During a public health crisis like the COVID-19 pandemic, a credible and easy-to-access information portal is highly desirable. It helps with disease prevention, public health planning, and misinformation mitigation. However, creating such an information portal is challenging because 1) domain expertise is required to identify and curate credible and intelligible content, 2) the information needs to be updated promptly in response to the fast-changing environment, and 3) the information should be easily accessible by the general public; which is particularly difficult when most people do not have the domain expertise about the crisis. In this paper, we presented an expert-sourcing framework and created Jennifer, an AI chatbot, which serves as a credible and easy-to-access information portal for individuals during the COVID-19 pandemic. Jennifer was created by a team of over 150 scientists and health professionals around the world, deployed in the real world and answered thousands of user questions about COVID-19. We evaluated Jennifer from two key stakeholders’ perspectives, expert volunteers and information seekers. We first interviewed experts who contributed to the collaborative creation of Jennifer to learn about the challenges in the process and opportunities for future improvement. We then conducted an online experiment that examined Jennifer’s effectiveness in supporting information seekers in locating COVID-19 information and gaining their trust. We share the key lessons learned and discuss design implications for building expert-sourced and AI-powered information portals, along with the risks and opportunities of misinformation mitigation and beyond.

The IEEE TRANSACTIONS ON SIGNAL PROCESSING is fortunate to attract submissions of the highest quality and to publish articles that deal with topics that are at the forefront of what is happening in the field of signal processing and its adjacent areas. ...

No abstract available.

Recent studies show the effectiveness of interview chatbots for information elicitation. However, designing an effective interview chatbot is non-trivial. Few tools exist to help designers design, evaluate, and improve an interview chatbot iteratively. Based on a formative study and literature reviews, we propose a computational framework for quantifying the performance of interview chatbots. Incorporating the framework, we have developed iChatProfile, an assistive chatbot design tool that can automatically generate a profile of an interview chatbot with quantified performance metrics and offer design suggestions for improving the chatbot based on such metrics. To validate the effectiveness of iChatProfile, we designed and conducted a between-subject study that compared the performance of 10 interview chatbots designed with or without using iChatProfile. Based on the live chats between the 10 chatbots and 1349 users, our results show that iChatProfile helped the designers build significantly more effective interview chatbots, improving both interview quality and user experience.

No abstract available.

Interview chatbots engage users in a text-based conversation to draw out their views and opinions. It is, however, challenging to build effective interview chatbots that can handle user free-text responses to open-ended questions and deliver engaging user experience. As the first step, we are investigating the feasibility and effectiveness of using publicly available, practical AI technologies to build effective interview chatbots. To demonstrate feasibility, we built a prototype scoped to enable interview chatbots with a subset of active listening skills-the abilities to comprehend a user's input and respond properly. To evaluate the effectiveness of our prototype, we compared the performance of interview chatbots with or without active listening skills on four common interview topics in a live evaluation with 206 users. Our work presents practical design implications for building effective interview chatbots, hybrid chatbot platforms, and empathetic chatbots beyond interview tasks.

Have you watched the movie Her? Have you ever wondered or wished to have an AI companion like Samantha, who could tell you what you really are, whom your best teammate may be, and which career path would be best for you? In this talk, Michelle will present a framework for building hyper-personalized, conversational Artificial Intelligent (AI) agents who can deeply understand users and responsibly guide user behavior in both virtual and real world. Through live demos, she will highlight two technical advances of the framework: (1) evidence-based personality inference and (2) model-based conversation generation. Michelle will discuss real-world applications of these agents and the wider implications of enabling hyper-personalized conversational AI agents for businesses and individuals.

The rise of increasingly more powerful chatbots offers a new way to collect information through conversational surveys, where a chatbot asks open-ended questions, interprets a user’s free-text responses, and probes answers whenever needed. To investigate the effectiveness and limitations of such a chatbot in conducting surveys, we conducted a field study involving about 600 participants. In this study with mostly open-ended questions, half of the participants took a typical online survey on Qualtrics and the other half interacted with an AI-powered chatbot to complete a conversational survey. Our detailed analysis of over 5,200 free-text responses revealed that the chatbot drove a significantly higher level of participant engagement and elicited significantly better quality responses measured by Gricean Maxims in terms of their informativeness, relevance, specificity, and clarity. Based on our results, we discuss design implications for creating AI-powered chatbots to conduct effective surveys and beyond.

We are building an intelligent agent to help teaming efforts. In this paper, we investigate the real-world use of such an agent to understand students deeply and help student team formation in a large university class involving about 200 students and 40 teams. Specifically, the agent interacted with each student in a text-based conversation at the beginning and end of the class. We show how the intelligent agent was able to elicit in-depth information from the students, infer the students' personality traits, and reveal the complex relationships between team personality compositions and team results. We also report on the students' behavior with and impression of the agent. We discuss the benefits and limitations of such an intelligent agent in helping team formation, and the design considerations for creating intelligent agents for aiding in teaming efforts.

Have you watched the movie Her? Have you ever wondered or wished to have your own AI companion just like Samantha, who could understand you better than you know about yourself, and could tell you what you really are, whom your best partner may be, and which career path would be best for you? In this talk, I will present a computational framework for building responsible and empathetic Artificial Intelligent (AI) agents who can deeply understand their users as unique individuals and responsibly guide their behavior in both virtual and real world.

We present artificial intelligent (AI) agents that act as interviewers to engage with a user in a text-based conversation and automatically infer the user's personality traits. We investigate how the personality of an AI interviewer and the inferred personality of a user influences the user's trust in the AI interviewer from two perspectives: the user's willingness to confide in and listen to an AI interviewer. We have developed two AI interviewers with distinct personalities and deployed them in a series of real-world events. We present findings from four such deployments involving 1,280 users, including 606 actual job applicants. Notably, users are more willing to confide in and listen to an AI interviewer with a serious, assertive personality in a high-stakes job interview. Moreover, users’ personality traits, inferred from their chat text, along with interview context, influence their perception of and their willingness to confide in and listen to an AI interviewer. Finally, we discuss the design implications of our work on building hyper-personalized, intelligent agents.

We present an intelligent virtual interviewer that engages with a user in a text-based conversation and automatically infers the user's psychological traits, such as personality. We investigate how the personality of a virtual interviewer influences a user's behavior from two perspectives: the user's willingness to confide in, and listen to, a virtual interviewer. We have developed two virtual interviewers with distinct personalities and deployed them in a real-world recruiting event. We present findings from completed interviews with 316 actual job applicants. Notably, users are more willing to confide in and listen to a virtual interviewer with a serious, assertive personality. Moreover, users' personality traits, inferred from their chat text, influence their perception of a virtual interviewer, and their willingness to confide in and listen to a virtual interviewer. Finally, we discuss the implications of our work on building hyper- personalized, intelligent agents based on user traits.

In this paper, we present computational models to predict Twitter users' attitude towards a specific brand through their personal and social characteristics. We also predict their likelihood of taking different actions based on their attitudes. In order to operationalize our research on users' attitude and actions, we collected ground-truth data through surveys of Twitter users. We have conducted experiments using two real world datasets to validate the effectiveness of our attitude and action prediction framework. Finally, we show how our models can be integrated with a visual analytics system for customer intervention.

other Share on Introduction to the Special Issue on Recommender System Benchmarking Authors: Paolo Cremonesi Politecnico di Milano Politecnico di MilanoView Profile , Alan Said Recorded Future Recorded FutureView Profile , Domonkos Tikk Gravity R&D, Hungary Gravity R&D, HungaryView Profile , Michelle X. Zhou Juji JujiView Profile Authors Info & Claims ACM Transactions on Intelligent Systems and TechnologyVolume 7Issue 3April 2016 Article No.: 38pp 1–4https://doi.org/10.1145/2870627Published:08 March 2016Publication History 2citation384DownloadsMetricsTotal Citations2Total Downloads384Last 12 Months12Last 6 weeks1 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

With the recent advances in using data analytics to automatically infer one's personality traits from their social media data, users are facing a growing tension between the use of the technology to aid self development in workplace and the privacy concerns of such use. Given the richness of personality data that can be derived today and the varied sensitivity of revealing such data, it is a non-trivial task for users to configure their privacy settings for sharing and protecting their derived personality data. Here we present the design, development, and evaluation of an interactive visualization tool, VeilMe, which helps users configure the privacy settings for the use of their personality portraits derived from social media. Unlike other privacy configuration tools, our tool offers two distinct advantages. First, it presents a novel and intuitive visual interface that aids users in understanding and exploring their own personality traits derived from their social media data, and configuring their privacy preferences. Second, our tool helps users to jump start their privacy settings by suggesting initial sharing strategies based on a set of factors, including the users' personality and target audience. We have evaluated the use of our tool with 124 participants in an enterprise context. Our results show that VeilMe effectively supports various user privacy configuration tasks, and also suggest several design implications, including the approaches to personalized privacy configurations.

There has been much effort on studying how social media sites, such as Twitter, help propagate information in different situations, including spreading alerts and SOS messages in an emergency. However, existing work has not addressed how to actively identify and engage the right strangers at the right time on social media to help effectively propagate intended information within a desired time frame. To address this problem, we have developed three models: (1) a feature-based model that leverages people's exhibited social behavior, including the content of their tweets and social interactions, to characterize their willingness and readiness to propagate information on Twitter via the act of retweeting; (2) a wait-time model based on a user's previous retweeting wait times to predict his or her next retweeting time when asked; and (3) a subset selection model that automatically selects a subset of people from a set of available people using probabilities predicted by the feature-based model and maximizes retweeting rate. Based on these three models, we build a recommender system that predicts the likelihood of a stranger to retweet information when asked, within a specific time window, and recommends the top-N qualified strangers to engage with. Our experiments, including live studies in the real world, demonstrate the effectiveness of our work.

There is much recent work on using the digital footprints left by people on social media to predict personal traits and gain a deeper understanding of individuals. Due to the veracity of social media, imperfections in prediction algorithms, and the sensitive nature of one's personal traits, much research is still needed to better understand the effectiveness of this line of work, including users' preferences of sharing their computationally derived traits. In this paper, we report a two- part study involving 256 participants, which (1) examines the feasibility and effectiveness of automatically deriving three types of personality traits from Twitter, including Big 5 personality, basic human values, and fundamental needs, and (2) investigates users' opinions of using and sharing these traits. Our findings show there is a potential feasibility of automatically deriving one's personality traits from social media with various factors impacting the accuracy of models. The results also indicate over 61.5% users are willing to share their derived traits in the workplace and that a number of factors significantly influence their sharing preferences. Since our findings demonstrate the feasibility of automatically inferring a user's personal traits from social media, we discuss their implications for designing a new generation of privacy-preserving, hyper-personalized systems.

Massive amounts of data are being generated on social media sites, such as Twitter and Facebook. These data can be used to better understand people (e.g., personality traits, perceptions, and preferences) and predict their behavior. As a result, a deeper understanding of users and their behavior can benefit a wide range of intelligent applications, such as advertising, social recommender systems, and personalized knowledge management. These applications will also benefit individual users themselves and optimize their experience across a wide variety of domains, such as retail, healthcare, and education. Since mining and understanding user behavior from social media often requires interdisciplinary effort, including machine learning, text mining, human-computer interaction, and social science, our workshop aims to bring together researchers and practitioners from multiple fields to discuss the creation of deeper models of individual users by mining the content that they publish and the social networking behavior that they exhibit.

There has been much effort on studying how social media sites, such as Twitter, help propagate information in different situations, including spreading alerts and SOS messages in an emergency. However, existing work has not addressed how to actively identify and engage the right strangers at the right time on social media to help effectively propagate intended information within a desired time frame. To ad-dress this problem, we have developed two models: (i) a feature-based model that leverages peoplesfi exhibited social behavior, including the content of their tweets and social interactions, to characterize their willingness and readiness to propagate information on Twitter via the act of retweeting; and (ii) a wait-time model based on a user's previous retweeting wait times to predict her next retweeting time when asked. Based on these two models, we build a recommender system that predicts the likelihood of a stranger to retweet information when asked, within a specific time window, and recommends the top-N qualified strangers to engage with. Our experiments, including live studies in the real world, demonstrate the effectiveness of our work.

On top of an enterprise social platform, we are building a smart social QA system that automatically routes questions to suitable employees who are willing, able, and ready to provide answers. Due to a lack of social QA history (training data) to start with, in this paper, we present an optimization-based approach that recommends both top-matched active (seed) and inactive (prospect) answerers for a given question. Our approach includes three parts. First, it uses a predictive model to find top-ranked seed answerers by their fitness, including their ability and willingness, to answer a question. Second, it uses distance metric learning to discover prospects most similar to the seeds identified in the first step. Third, it uses a constraint-based approach to balance the selection of both seeds and prospects identified in the first two steps. As a result, not only does our solution route questions to top-matched active users, but it also engages inactive users to grow the pool of answerers. Our real-world experiments that routed 114 questions to 684 people identified from 400,000+ employees included 641 prospects (93.7%) and achieved about 70% answering rate with 83% of answers received a lot/full confidence.

This paper presents a system, System U, which automatically derives people's personality traits from social media and recommends people for different tasks. The system leverages linguistic signals appearing in a person's social media activities to compute the personality portraits including Big Five personality, fundamental needs and basic human values. This system and technology can be used in a wide variety of personalized applications, such as recommending people to answer questions.

We are developing an automated visualization system that helps users combine two or more existing information graphics to form an integrated view. To establish empirical foundations for building such a system, we designed and conducted two studies on Amazon Mechanical Turk to understand users’ comprehension and preferences of composite visualization under different conditions (e.g., data and tasks). In Study 1, we collected more than 1,500 textual descriptions capturing about 500 participants’ insights of given information graphics, which resulted in a task-oriented taxonomy of visual insights. In Study 2, we asked 240 participants to rank composite visualizations by their suitability for acquiring a given visual insight identified in Study 1, which resulted in ranked user preferences of visual compositions for acquiring each type of insight. In this article, we report the details of our two studies and discuss the broader implications of our crowdsourced research methodology and results to HCI-driven visualization research.

Online communities are increasingly being deployed in enterprises to increase productivity and share expertise. Community leaders are critical for fostering successful communities, but existing technologies rarely support leaders directly, both because of a lack of clear data about leader needs, and because existing tools are member- rather than leader-centric. We present the evidence-based design and evaluation of a novel tool for community leaders, Community Insights (CI). CI provides actionable analytics that help community leaders foster healthy communities, providing value to both members and the organization. We describe empirical and system contributions derived from a long-term deployment of CI to leaders of 470 communities over 10 months. Empirical contributions include new data showing: (a) which metrics are most useful for leaders to assess community health, (b) the need for and how to design actionable metrics, (c) the need for and how to design contextualized analytics to support sensemaking about community data. These findings motivate a novel community system that provides leaders with useful, actionable and contextualized analytics.

Massive amounts of data are being generated on social media sites, such as Twitter and Facebook. These data can be used to better understand people (e.g., personality traits, perceptions, and preferences) and predict their behavior. As a result, a deeper understanding of users and their behavior can benefit a wide range of intelligent applications, such as advertising, social recommender systems, and personalized knowledge management. These applications will also benefit individual users themselves and optimize their experience across a wide variety of domains, such as retail, healthcare, and education. Since mining and understanding user behavior from social media often requires interdisciplinary effort, including machine learning, text mining, human-computer interaction, and social science, our workshop aims to bring together researchers and practitioners from multiple fields to discuss the creation of deeper models of individual users by mining the content that they publish and the social networking behavior that they exhibit.

An online community consists of a group of users who share a common interest, background, or experience and their collective goal is to contribute towards the welfare of the community members. Question answering is an important feature that enables community members to exchange knowledge within the community boundary. The overwhelming number of communities necessitates the need for a good question routing strategy so that new questions gets routed to the appropriately focused community and thus get resolved. In this paper, we consider the novel problem of routing questions to the right community and propose a framework to select the right set of communities for a question. We begin by using several prior proposed features for users and add some additional features, namely language attributes and inclination to respond, for community modeling. Then we introduce two k nearest neighbor based aggregation algorithms for computing community scores. We show how these scores can be combined to recommend communities and test the effectiveness of the recommendations over a large real world dataset.

The emergence of social media creates a unique opportunity for developing a new class of crowd-powered information collection systems. Such systems actively identify potential users based on their public social media posts and solicit them directly for information. While studies have shown that users will respond to solicitations in a few domains, there is little analysis of the quality of information received. Here we explore the quality of information solicited from Twitter users in the domain of product reviews, specifically reviews for a popular tablet computer and L.A.-based food trucks. Our results show that the majority of responses to our questions (>70%) contained relevant information and often provided additional details (>37%) beyond the topic of the question. We compare the solicited Twitter reviews to other user-generated reviews from Amazon and Yelp, and found that the Twitter answers provided similar information when controlling for the questions asked. Our results also reveal limitations of this new information collection method, including its suitability in certain domains and potential technical barriers to its implementation. Our work provides strong evidence for the potential of this new class of information collection systems and design implications for their future use.

Finding the right person to ask for help is a difficult task within a large enterprise. While there are a few studies detailing practices for finding an expert often in the context of an expertise locator system, there are fewer studies on workplace practices and challenges for finding a person who can help, especially independent of any particular technology. We conducted a two-part study of helper-finding activities with 36 enterprise workers, representing different job roles and levels of experience. First, we present a taxonomy of workplace helper-finding needs that involves tasks, topics, and helper selection criteria, developed by analyzing two weeks of participant diaries describing helper-finding problems. Second, we present the results of follow-up interviews with each participant, focusing on helper-finding challenges in the workplace. Finally, we present design implications for systems aimed at supporting helper-finding in the workplace.

We present an intelligent, crowd-powered information collection system that automatically identifies and asks targeted strangers on Twitter for desired information (e.g., current wait time at a nightclub). Our work includes three parts. First, we identify a set of features that characterize one's willingness and readiness to respond based on their exhibited social behavior, including the content of their tweets and social interaction patterns. Second, we use the identified features to build a statistical model that predicts one's likelihood to respond to information solicitations. Third, we develop a recommendation algorithm that selects a set of targeted strangers using the probabilities computed by our statistical model with the goal to maximize the over-all response rate. Our experiments, including several in the real world, demonstrate the effectiveness of our work.

We are building a topic-based, interactive visual analytic tool that aids users in analyzing large collections of text. To help users quickly discover content evolution and significant content transitions within a topic over time, here we present a novel, constraint-based approach to temporal topic segmentation. Our solution splits a discovered topic into multiple linear, non-overlapping sub-topics along a timeline by satisfying a diverse set of semantic, temporal, and visualization constraints simultaneously. For each derived sub-topic, our solution also automatically selects a set of representative keywords to summarize the main content of the sub-topic. Our extensive evaluation, including a crowd-sourced user study, demonstrates the effectiveness of our method over an existing baseline.

Information graphics have been used for thousands of years to help illustrate ideas and communicate information. However, it requires skills and time to hand craft high-quality, customized information graphics for specific situations (e.g., data characteristics and user tasks). The problem becomes more acute when we must deal with big data. To address this problem, we are researching and developing mixed-initiative visual analytic systems that leverage both the intelligence of humans and machines to aid users in deriving insights from massive data. On the one hand, such a system automatically guides users to perform their data analytic tasks by recommending suitable visualization and discovery paths in context. On the other hand, users interactively explore, verify, and improve visual analytic results, which in turn helps the system to learn from users' behavior and improve its quality over time. In this talk, I will present key technologies that we have developed in building mixed-initiative visual analytic systems, including feature-based visualization recommendation and optimization-based approaches to dynamic data transformation for more effective visualization. I will also use concrete applications to demonstrate the use and value of mixed-initiative visual analytic systems, and discuss existing challenges and future directions in this area.

No abstract available.

In this paper, we propose a novel constrained coclustering method to achieve two goals. First, we combine information-theoretic coclustering and constrained clustering to improve clustering performance. Second, we adopt both supervised and unsupervised constraints to demonstrate the effectiveness of our algorithm. The unsupervised constraints are automatically derived from existing knowledge sources, thus saving the effort and cost of using manually labeled constraints. To achieve our first goal, we develop a two-sided hidden Markov random field (HMRF) model to represent both document and word constraints. We then use an alternating expectation maximization (EM) algorithm to optimize the model. We also propose two novel methods to automatically construct and incorporate document and word constraints to support unsupervised constrained clustering: 1) automatically construct document constraints based on overlapping named entities (NE) extracted by an NE extractor; 2) automatically construct word constraints based on their semantic distance inferred from WordNet. The results of our evaluation over two benchmark data sets demonstrate the superiority of our approaches against a number of existing approaches.

Expertise selection is the process of choosing an expert from a list of recommended people. This is an important and nuanced step in expertise location that has not received a great deal of attention. Through a lab-based, controlled investigation with 35 enterprise workers, we found that presenting additional information about each recommended person in a search result list led the participants to make quicker and better-informed selections. These results focus attention on a currently understudied aspect of expertise location--expertise selection--that could greatly improve the usefulness of supporting systems. We also asked participants to rate the type of information that might be most useful for expertise selection on a paper prototype containing 36 types of potentially helpful information. We identified sixteen types of this information that may be most useful for various expertise selection tasks.

Massive amounts of data are being generated on social media sites, such as Twitter and Facebook. This data can be used to better understand people, such as their personality traits, perceptions, and preferences, and predict their behavior. This deeper understanding of users and their behaviors can benefit a wide range of intelligent applications, such as advertising, social recommender systems, and personalized knowledge management. These applications will also benefit individual users themselves by optimizing their experiences across a wide variety of domains, such as retail, healthcare, and education. Since mining and understanding user behavior from social media often requires interdisciplinary effort, including machine learning, text mining, human-computer interaction, and social science, our workshop aims to bring together researchers and practitioners from multiple fields to discuss the creation of deeper models of individual users by mining the content that they publish and the social networking behavior that they exhibit.

In this paper, we present a case study of MoCo Blogs, a publicly accessible, corporate blogging site, which is hosted by a large telecommunication company in China. We study the design and operation of the site from two aspects: (1) how community owners/administrators guide and coordinate blogger activities to meet the company's business goals; and (2) how participants respond to management guidance and act on their own incentives. Through the analysis of three data sources: 17-month activity logs with 1,046 bloggers and 10,291 blog entries, 4-month online participatory observation, and in-depth interviews, we present two key findings. First, we describe three key operational strategies employed by the site administrative team to encourage user contributions and manage content across the organizational boundaries. Second, we examine how these strategies directly influence user participation. Finally, we discuss the implications of our findings on an organization's roles in corporate social communities.

Massive amounts of data are being generated on social media sites, such as Twitter and Facebook. People from all walks of life share data about social events, express opinions, discuss their interests, publicize businesses, recommend products, and, explicitly or implicitly, reveal personal information. This workshop will focus on the use of social media data for creating models of individual users from the content that they publish. Deeper understanding of user behavior and associated attributes can benefit a wide range of intelligent applications, such as social recommender systems and expert finders, as well as provide the foundation in support of novel user interfaces (e.g., actively engaging the crowd in mixed-initiative question-answering systems). These applications and interfaces may offer significant benefits to users across a wide variety of domains, such as retail, government, healthcare and education. User modeling from public social media data may also reveal information that users would prefer to keep private. Such concerns are particularly important because individuals do not have complete control over the information they share about themselves. For example, friends of a user may inadvertently divulge private information about that user in their own posts. In this workshop we will also discuss possible mechanisms that users might employ to monitor what information has been revealed about themselves on social media and obfuscate any sensitive information that has been accidentally revealed.

REACH is an intelligent, people-finding system that helps users to find someone in their social directory, especially those whom they do not fully remember or barely know. It analyzes a user's communication and social networking data to automatically extract all the contacts and derive multiple facets to characterize each contact in relation to the user. It then employs a personalized, faceted search to retrieve and present a ranked list of matched contacts based on their properties. A preliminary evaluation shows the effectiveness of our approach.

Elsevier’s Scopus, the largest abstract and citation database of peer-reviewed literature. Search and access research from the science, technology, medicine, social sciences and arts and humanities fields.

We are building an interactive visual text analysis tool that aids users in analyzing large collections of text. Unlike existing work in visual text analytics, which focuses either on developing sophisticated text analytic techniques or inventing novel text visualization metaphors, ours tightly integrates state-of-the-art text analytics with interactive visualization to maximize the value of both. In this article, we present our work from two aspects. We first introduce an enhanced, LDA-based topic analysis technique that automatically derives a set of topics to summarize a collection of documents and their content evolution over time. To help users understand the complex summarization results produced by our topic analysis technique, we then present the design and development of a time-based visualization of the results. Furthermore, we provide users with a set of rich interaction tools that help them further interpret the visualized results in context and examine the text collection from multiple perspectives. As a result, our work offers three unique contributions. First, we present an enhanced topic modeling technique to provide users with a time-sensitive and more meaningful text summary. Second, we develop an effective visual metaphor to transform abstract and often complex text summarization results into a comprehensible visual representation. Third, we offer users flexible visual interaction tools as alternatives to compensate for the deficiencies of current text summarization techniques. We have applied our work to a number of text corpora and our evaluation shows promise, especially in support of complex text analyses.

Dandelion is a wiki-based tool that supports coordinated, collaborative authoring. In this paper, we present an ex-tended version of Dandelion, which provides an email inter-face for users to accomplish their tasks by email in a coordinated, collaborative authoring process. Specifically, Dandelion employs a semi-structured, template-based approach that allows users to use templates to specify their requests in email. These emailed requests can be interpreted by Dandelion and are then used to automatically drive the collaboration flow. As part of its actions, Dandelion automatically creates a wiki page and dynamically updates it to record co-authoring tasks and collate co-authored content. As a result, users can use their familiar tool (email) to accomplish their tasks in a co-authoring process, while leveraging a wiki for additional benefits (e.g., obtaining collaboration awareness and formatting the text). Our preliminary study with two groups of users shows the usefulness of both Dandelion email and wiki features and their impact on collaboration effectiveness.

In this paper we feature a set of research projects done at several IBM Research laboratories across the world. The work featured here focuses on the topic of smart social collaboration, which studies, designs, and develops social collaboration principles and technologies that can help customize and enhance existing social collaboration tools to suit specific user needs, including cultural, business, and personal needs.

No abstract available.

Content-centric social Web sites, such as discussion forums and blog sites, have flourished during the past several years. These sites often contain overwhelming amounts of information that are also being updated rapidly. To help users locate their interests at such sites (e.g., interesting blogs to read or discussion forums to join), researchers have developed a number of recommendation technologies. However, it is difficult to make effective recommendations for new users (a.k.a. the cold start problem) due to a lack of user information (e.g., preferences and interests). Furthermore, the complexity of recommendation algorithms often prevents users from comprehending let alone trusting the recommended results. To tackle these above two challenges, we are building a social map-based recommender system called Pharos. A social map summarizes users’ content-related social behavior over time (e.g., reading, writing, and commenting behavior during the past week) as a set of latent communities. For a given time interval, each community is characterized by the theme of the content being discussed and the key people involved. By discovering, ranking, and displaying the most popular latent communities at different time intervals, Pharos creates a time-sensitive, visual social map of a Web site. This enables new users to obtain a quick overview of the site, alleviating the cold start problem. Furthermore, we use the social map as a context to help explain Pharos-recommended content and people. Users can also interactively explore the social map to locate the content in which they are interested or people that are not being explicitly recommended, compensating for the imperfections in the recommendation algorithms. We have developed several Pharos applications, one of which is deployed within our company. Our preliminary evaluation of the deployed application shows the usefulness of Pharos.

In this paper, we present a constrained co-clustering approach for clustering textual documents. Our approach combines the benefits of information-theoretic co-clustering and constrained clustering. We use a two-sided hidden Markov random field (HMRF) to model both the document and word constraints. We also develop an alternating expectation maximization (EM) algorithm to optimize the constrained co-clustering model. We have conducted two sets of experiments on a benchmark data set: (1) using human-provided category labels to derive document and word constraints for semi-supervised document clustering, and (2) using automatically extracted named entities to derive document constraints for unsupervised document clustering. Compared to several representative constrained clustering and co-clustering approaches, our approach is shown to be more effective for high-dimensional, sparse text data.

In this paper, we introduce a visualization method that couples a trend chart with word clouds to illustrate temporal content evolutions in a set of documents. Specifically, we use a trend chart to encode the overall semantic evolution of document content over time. In our work, semantic evolution of a document collection is modeled by varied significance of document content, represented by a set of representative keywords, at different time points. At each time point, we also use a word cloud to depict the representative keywords. Since the words in a word cloud may vary one from another over time (e.g., words with increased importance), we use geometry meshes and an adaptive force-directed model to lay out word clouds to highlight the word differences between any two subsequent word clouds. Our method also ensures semantic coherence and spatial stability of word clouds over time. Our work is embodied in an interactive visual analysis system that helps users to perform text analysis and derive insights from a large collection of documents. Our preliminary evaluation demonstrates the usefulness and usability of our work.

Dandelion is a tool that extends wikis to support coordinated, collaborative authoring using a tag-based approach. Specifically, users can insert tags in a wiki page to specify various co-authoring tasks. These tags can then be executed to help drive and manage the collaboration workflow, and provide content-centric collaboration awareness for all the co-authors. Four successful pilot deployments and positive user feedback show the practical value of Dandelion, especially its value in supporting a structured, collaborative authoring process often seen in business settings.

Existing studies of online social communities mainly focus on communities in the United States. Since Chinese social beliefs and behaviors largely differ from that of Americans, we hypothesize that Chinese online communities also greatly differ from their U.S. counterparts. In particular, we believe that Chinese online communities must balance management control and individual autonomy to accommodate both Chinese tradition and the social nature of online societies. In this paper, we present three studies to test our hypothesis. First, we use a structured observation (Study I) to examine community governance practices of 32 Chinese and American social sites. Based on the identified community governance practices, we use a cross-cultural survey of 208 Chinese and Americans (Study II) to learn about their behavior and attitude toward these practices. Finally, we interview 38 Chinese users (Study III) to help us further understand how Chinese online communities balance the needs of management and users. Not only do the studies confirm our hypothesis, but they also help us abstract two key design implications of social software to meet the needs of Chinese.

Over the past decades, there have been significant efforts on developing robust and easy-to-use query interfaces to databases. So far, the typical query interfaces are GUI-based visual query interfaces. Visual query interfaces however, have limitations especially when they are used for accessing large and complex datasets. Therefore, we are developing a novel query interface where users can use natural language expressions to help author visual queries. Our work enhances the usability of a visual query interface by directly addressing the "knowledge gap" issue in visual query interfaces. We have applied our work in several real-world applications. Our preliminary evaluation demonstrates the effectiveness of our approach

This workshop brought researchers from academia and industry together to share recent advances and discuss research directions for recommender systems in social media and Web 2.0. With social media sites becoming ubiquitous, the challenges and opportunities for recommendation technologies become greater, setting the grounds for new research and innovation.

This workshop brought together researchers and practitioners from both text analytics and interactive visualization communities to explore, define, and develop intelligent visual interfaces that help enhance the consumption and quality of complex text analysis results. Using this workshop as a starting point, we aim to foster closer, interdisciplinary relationships among researchers from text analytics and interactive visualization communities, so they can combine their expertise together to better tackle the difficult problems that face the text analytics community today.

In this paper, we present a novel exploratory visual analytic system called TIARA (Text Insight via Automated Responsive Analytics), which combines text analytics and interactive visualization to help users explore and analyze large collections of text. Given a collection of documents, TIARA first uses topic analysis techniques to summarize the documents into a set of topics, each of which is represented by a set of keywords. In addition to extracting topics, TIARA derives time-sensitive keywords to depict the content evolution of each topic over time. To help users understand the topic-based summarization results, TIARA employs several interactive text visualization techniques to explain the summarization results and seamlessly link such results to the original text. We have applied TIARA to several real-world applications, including email summarization and patient record analysis. To measure the effectiveness of TIARA, we have conducted several experiments. Our experimental results and initial user feedback suggest that TIARA is effective in aiding users in their exploratory text analytic tasks.

Content-centric social websites, such as discussion forums and blog sites, have flourished during the past several years. These sites often contain overwhelming amounts of information that are also being updated rapidly. To help users locate their interests at such sites (e.g., interesting blogs to read or discussion forums to join), researchers have developed a number of recommendation technologies. However, it is difficult to make effective recommendations for new users (a.k.a. the cold start problem) due to a lack of user information (e.g., preferences and interests). Furthermore, the complexity of recommendation algorithms often prevents users from comprehending let alone trusting the recommended results. To tackle the above two challenges, we are building a social map-based recommender system called Pharos. A social map summarizes users' content-related social behavior over time (e.g., reading, writing, and commenting behavior during the past week) as a set of latent communities. Each community is characterized by the theme of the content being discussed and the key people involved. By discovering, ranking, and displaying the most "popular" latent communities, Pharos creates a visual social map of a website. This enables new users to obtain a quick overview of the site, alleviating the cold start problem. Furthermore, we use the social map as a context to help explain Pharos-recommended content and people. Users can also interactively explore the social map to locate their interested content or people that are not being explicitly recommended, compensating for the imperfection in the recommendation algorithms. We have deployed Pharos within our company and our preliminary evaluation shows the usefulness of Pharos.

No abstract available.

We are building an interactive, visual text analysis tool that aids users in analyzing a large collection of text. Unlike existing work in text analysis, which focuses either on developing sophisticated text analytic techniques or inventing novel visualization metaphors, ours is tightly integrating state-of-the-art text analytics with interactive visualization to maximize the value of both. In this paper, we focus on describing our work from two aspects. First, we present the design and development of a time-based, visual text summary that effectively conveys complex text summarization results produced by the Latent Dirichlet Allocation (LDA) model. Second, we describe a set of rich interaction tools that allow users to work with a created visual text summary to further interpret the summarization results in context and examine the text collection from multiple perspectives. As a result, our work offers two unique contributions. First, we provide an effective visual metaphor that transforms complex and even imperfect text summarization results into a comprehensible visual summary of texts. Second, we offer users a set of flexible visual interaction tools as the alternatives to compensate for the deficiencies of current text summarization techniques. We have applied our work to a number of text corpora and our evaluation shows the promise of the work, especially in support of complex text analyses.

Topic-based text summaries promise to help average users quickly understand a text collection and derive insights. Recent research has shown that the Latent Dirichlet Allocation (LDA) model is one of the most effective approaches to topic analysis. However, the LDA-based results may not be ideal for human understanding and consumption. In this paper, we present several topic and keyword re-ranking approaches that can help users better understand and consume the LDA-derived topics in their text analysis. Our methods process the LDA output based on a set of criteria that model a user's information needs. Our evaluation demonstrates the usefulness of the methods in summarizing several large-scale, real world data sets.

We are building an interactive, smart notepad system where users enter brief notes to drive a dynamic information-seeking process. In this paper, we focus on describing our work from two aspects: 1) dynamic interpretation of user notes in context to infer a user's information needs, and 2) automatic generation of data queries to satisfy the inferred user needs. Compared to existing information systems, our work offers three unique contributions. First, our system allows users to focus on what to retrieve instead of how, since users can use brief notes to express their information needs without worrying about specific retrieval details. Second, users can use notes to efficiently request multiple pieces of information at once instead of issuing one query at a time. Third, users can easily update any part of their notes to obtain new or updated information. Whenever a user's notes are modified, our system automatically detects and evaluates all affected note sections to retrieve new or updated information. Our preliminary evaluation shows the promise of this work.

We are building a smart visual dialog system that aids users in investigating large and complex data sets. Given a user's data request, we automate the generation of a visual response that is tailored to the user's context. In this paper, we focus on the problem of data transformation, which is the process of preparing the raw data (e.g., cleaning and scaling) for effective visualization. Specifically, we develop an optimization-based approach to data transformation. Compared to existing approaches, which normally focus on specific transformation techniques, our work addresses how to dynamically determine proper data transformations for a wide variety of visualization situations. As a result, our work offers two unique contributions. First, we provide a general computational framework that can dynamically derive a set of data transformations to help optimize the quality of the target visualization. Second, we provide an extensible, feature-based model to uniformly represent various data transformation operations and visualization quality metrics. Our evaluation shows that our work significantly improves visualization quality and helps users to better perform their tasks.

Data transformation, the process of preparing raw data for effective visualization, is one of the key challenges in information visualization. Although researchers have developed many data transformation techniques, there is little empirical study of the general impact of data transformation on visualization. Without such study, it is difficult to systematically decide when and which data transformation techniques are needed. We thus have designed and conducted a two-part empirical study that examines how the use of common data transformation techniques impacts visualization quality, which in turn affects user task performance. Our first experiment studies the impact of data transformation on user performance in single-step, typical visual analytic tasks. The second experiment assesses the impact of data transformation in multi-step analytic tasks. Our results quantify the benefits of data transformation in both experiments. More importantly, our analyses reveal that (1) the benefits of data transformation vary significantly by task and by visualization, and (2) the use of data transformation depends on a user's interaction context. Based on our findings, we present a set of design recommendations that help guide the development and use of data transformation techniques.

We are building an intelligent information system to aid users in their investigative tasks, such as detecting fraud. In such a task, users must progressively search and analyze relevant information before drawing a conclusion. In this paper, we address how to help users find relevant informa-tion during an investigation. Specifically, we present a novel approach that can improve information retrieval by exploiting a user's investigative context. Compared to existing retrieval systems, which are either context insensitive or leverage only limited user context, our work offers two unique contributions. First, our system works with users cooperatively to build an investigative context, which is otherwise very difficult to capture by machine or human alone. Second, we develop a context-aware method that can adaptively retrieve and evaluate information relevant to an ongoing investigation. Experiments show that our approach can improve the relevance of retrieved information significantly. As a result, users can fulfill their investigative tasks more efficiently and effectively.

Information seeking is an important but often difficult task, especially when it involves large and complex data sets. We hypothesize that a context-sensitive interaction paradigm would greatly assist users in their information seeking. Such a paradigm would allow users to both express their requests and receive requested information in context. Driven by this hypothesis, we have taken rigorous steps to design, develop, and evaluate a full-fledged, context-sensitive information system. We started with a Wizard-of-OZ (WOZ) study to verify the effectiveness of our envi-sioned system. We then built a fully automated system based on the findings from our WOZ study. We targeted the development and integration of two sets of technologies: context-sensitive mul-timodal input interpretation and multimedia output generation. Finally, we formally evaluated the usability of our system in real world conditions. The results show that our system greatly improves the users' ability to perform practical information-seek-ing tasks. These results not only confirm our initial hypothesis, but they also indicate the practicality of our approaches.

Multimodal conversation systems allow users to interact with computers effectively using multiple modalities, such as natural language and gesture. However, these systems have not been widely used in practical applications mainly due to their limited input understanding capability. As a result, conversation systems often fail to understand user requests and leave users frustrated. To address this issue, most existing approaches focus on improving a system's interpretation capability. Nonetheless, such improvements may still be limited, since they would never cover the entire range of input expressions. Alternatively, we present a two-way adaptation framework that allows both users and systems to dynamically adapt to each other's capability and needs during the course of interaction. Compared to existing methods, our approach offers two unique contributions. First, it improves the usability and robustness of a conversation system by helping users to dynamically learn the system's capabilities in context. Second, our approach enhances the overall interpretation capability of a conversation system by learning new user expressions on the fly. Our preliminary evaluation shows the promise of this approach.

To aid users in exploring large and complex data sets, we are building an intelligent multimedia conversation system. Given a user request, our system dynamically creates a multimedia response that is tailored to the interaction context. In this paper, we focus on the problem of media allocation, a process that assigns one or more media, such as graphics or speech, to best convey the intended response content. Specifically, we develop a graph-matching approach to media allocation, whose goal is to find a set of data-media mappings that maximizes the satisfaction of various allocation constraints (e.g., data-media compatibility and presentation consistency constraints). Compared to existing rule-based or plan-based approaches to media allocation, our work offers three unique contributions. First, we provide an extensible computational framework that optimizes media assignments by dynamically balancing all relevant constraints. Second, we use feature-based metrics to uniformly model various allocation constraints, including those cross-content and cross-media constraints, which often require special treatment in existing approaches. Third, we further improve the quality of a response by automatically detecting and repairing undesired allocation results. We have applied our approach to two different applications and our preliminary study has shown the promise of our work.

In a multimodal conversation, the way users communicate with a system depends on the available interaction channels and the situated context (e.g., conversation focus, visual feedback). These dependencies form a rich set of constraints from various perspectives such as temporal alignments between different modalities, coherence of conversation, and the domain semantics. There is strong evidence that competition and ranking of these constraints is important to achieve an optimal interpretation. Thus, we have developed an optimization approach for multimodal interpretation, particularly for interpreting multimodal references. A preliminary evaluation indicates the effectiveness of this approach, especially for complex user inputs that involve multiple referring expressions in a speech utterance and multiple gestures.

Multimodal user interfaces allow users to interact with computers through multiple modalities, such as speech, gesture, and gaze. To be effective, multimodal user interfaces must correctly identify all objects which users refer to in their inputs. To systematically resolve different types of references, we have developed a probabilistic approach that uses a graph-matching algorithm. Our approach identifies the most probable referents by optimizing the satisfaction of semantic, temporal, and contextual constraints simultaneously. Our preliminary user study results indicate that our approach can successfully resolve a wide variety of referring expressions, ranging from simple to complex and from precise to ambiguous ones.

We are building a multimedia conversation system to facilitate information seeking in large and complex data spaces. To provide tailored responses to diverse user queries introduced during a conversation, we automate the generation of a system response. Here we focus on the problem of determining the data content of a response. Specifically, we develop an optimization-based approach to content selection. Compared to existing rule-based or plan-based approaches, our work offers three unique contributions. First, our approach provides a general framework that effectively addresses content selection for various interaction situations by balancing a comprehensive set of constraints (e.g., content quality and quantity constraints). Second, our method is easily extensible, since it uses feature-based metrics to systematically model selection constraints. Third, our method improves selection results by incorporating content organization and media allocation effects, which otherwise are treated separately. Preliminary studies show that our method can handle most of the user situations identified in a Wizard-of-Oz study, and achieves results similar to those produced by human designers.

In a multimodal human-machine conversation, user inputs are often abbreviated or imprecise. Sometimes, merely fusing multimodal inputs together cannot derive a complete understanding. To address these inadequacies, we are building a semantics-based multimodal interpretation framework called MIND (Multimodal Interpretation for Natural Dialog). The unique feature of MIND is the use of a variety of contexts (e.g., domain context and conversation context) to enhance multimodal fusion. In this paper we present a semantically rich modeling scheme and a context-based approach that enable MIND to gain a full understanding of user inputs, including ambiguous and incomplete ones.

To support a full-fledged, multimedia human-computer conversation, we are building an intelligent framework, called Responsive Information Architect (RIA), which can automatically synthesize multimedia responses during the conversation. As part of its visual response generation, RIA dynamically creates context-sensitive interaction controls that are visual interfaces through which users can further interact with RIA. To enable the systematic design of interaction controls, we study and abstract control properties. In particular, in this paper we present a semantic model that captures the intentional, presentational, and behavioral characteristics of interaction controls. Using this model, we show how to systematically sketch the semantics of an interaction control.

We are building a full-fledged multimedia conversation framework called Responsive Information Architect (RIA), using a combination of AI and multimedia techniques. Here we describe RIA's capability of automated authoring of a coherent multimedia discourse, which is used by RIA to express itself when conversing with a user. Specifically, we focus on explaining three unique features of our automated authoring approach: automated authoring of multimedia interaction acts, dynamic insertion of multimedia punctuation acts, and systematic design of cross-media acts.

To develop a comprehensive and systematic approach to the automated design of visual discourse, we introduce a visual task taxonomy that interfaces high-level presentation intents with low-level visual techniques.In our approach, visual tasks describe presentation intents through their visual accomplishments, and suggest desired visual techniques through their visual implications.Therefore, we can characterize visual tasks by their visual accomplishments and implications.Through this characterization, visual tasks can guide the visual discourse synthesis process by specifying what presentation intents can be achieved and how to achieve them.

A visual discourse is a series of connected visual displays. A coherent visual discourse is characterized by smooth transitions between displays, consistent design within and across displays, and successful integration of new information into existing displays. We use a topdown, hierarchical-decomposition, partial order planner to efficiently construct a visual discourse from scratch, taking advantage of parametrized primitive visual objects that serve as building blocks in the design process. Visual representations are modeled as visual objects, graphical techniques are employed as planning operators, and design policies are encoded as constraints. This approach not only improves computational efficiency compared to search-based approaches, but also facilitates knowledge encoding, and ensures global coherency.

A visual discourse is a series of connected visual displays. A coherent visual discourse requires smooth transitions between displays, consistent design within and across displays, and successful integration of new information into existing displays. We present an approach for automatically designing a coherent visual discourse. A top-down, hierarchical-decomposition partial-order planner is used to efficiently plan the visual discourse. Visual representations are modelled as visual objects, graphical techniques are employed as planning operators, and design policies are encoded as constraints. This approach not only improves the computational efficiency compared to search-based approaches, but also facilitates knowledge encoding, and ensures global coherency. Keywords: Top-down hierarchical planning, automated graphics generation, knowledge-based user interfaces.

Creating high-quality multimedia presentations requires much skill, time, and effort.This is particularly true when temporal media, such as speech and animation, are involved.We describe the design and implementation of a knowledge-based system that generates customized temporal multimedia presentations.We provide art overview of the system's architecture, and explain how speech, written text, and graphics are generated and coordinated.Our emphasis is on how temporal media are coordinated by the system through a multi-stage negotiation process.In negotiation, media-specific generation components interact with a novel coordination component that solves temporal constraints provided by the generators.We illustrate our work with a set of examples generated by the system in a testbed application intended to update hospital caregivers on the status of patients who have undergone a cardiac bypass operation.

Just as broadband networks will enable user-to-user communications to extend from textural services to those employing multimedia, they will also enable a management environment that can take advantage of increased bandwidth and multimedia technology. The fundamental advances incorporated in such an environment can provide efficient solutions to the problem of information management. To establish this environment, the authors tackle the fundamental problems of observability and controllability of broadband networks. A virtual world provides a next-generation network management interface through which a user can observe and interact with the network directly in real time. The system that the authors are developing uses a 3D virtual world as the user interface for managing a large gigabit ATM network. It provides the capability for experimentation in all aspects of network transport, control and management.>