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.

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 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.

Individual differences matter. While this has been the theme for many recent works in the Visualization and HCI communities, the mystery of how to develop personalized visualizations remains. This is largely because very little is known about how users actually use visualizations to solve problems and even less is known about how individual differences affect these problem-solving strategies. In this paper, we provide evidence that strategies are indeed influenced by individual differences. We demonstrate how the personality trait locus of control impacts strategies on hierarchical visualizations, and we introduce design recommendations for personalized visualizations.

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.

In this paper, we present a comprehensive study of the relationship between an individual's personal traits and his/her brand preferences.In our analysis, we included a large number of character traits such as personality, personal values and individual needs.These trait features were obtained from both a psychometric survey and automated social media analytics.We also included an extensive set of brand names from diverse product categories.From this analysis, we want to shed some light on (1) whether it is possible to use personal traits to infer an individual's brand preferences (2) whether the trait features automatically inferred from social media are good proxies for the ground truth character traits in brand preference prediction.

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.

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.

Text analytics, an increasingly important application domain, is hampered by the high barrier to entry due to the many conceptual difficulties novice developers encounter. This work addresses the problem by developing a tool to guide novice developers to adopt the best practices employed by expert developers in text analytics and to quickly harness the full power of the underlying system. Taking a user centered task analytical approach, the tool development went through multiple design iterations and evaluation cycles. In the latest evaluation, we found that our tool enables novice developers to develop high quality extractors on par with the state of art within a few hours and with minimal training. Finally, we discuss our experience and lessons learned in the context of designing user interfaces to reduce the barriers to entry into complex domains of expertise.

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.

Enterprise search is challenging due to various reasons, notably the dynamic terminology and domain structure that are specific to the enterprise, combined with the fact that search deployments are typically managed by domain experts who are not necessarily search experts. To address that, it has been proposed to design search architectures that feature two principles: comprehensibility of the ranking mechanism and customizability of the search engine by means of intuitive runtime rules. The proposed demonstration operates on top of an engine implementation based on this search philosophy, and provides an administrator toolkit to realize the two principles. In particular, the toolkit provides a complete visualization of the provenance (hence ranking) of search results, embeds an editor for programming runtime rules, facilitates the investigation of (the cause of) missing or low-ranked desired results, and provides suggestions of rewrite rules to handle such results.

Browsing a collection of information on a mobile device is a common task, yet it can be difficult due to the small size of mobile displays. A common trade-off offered by many current mobile interfaces is to allow users to switch between an overview and detailed views of particular items. An open question is how much preview of each item to include in the overview. Using a mobile email processing task, we attempted to answer that question. We investigated participants' email processing behaviors under differing preview conditions in a semi-controlled, naturalistic study. We collected log data of participants' actual behaviors as well as their subjective impressions of different conditions. Our results suggest that a moderate level of two to three lines of preview should be the default. The overall benefit of a moderate amount of preview was supported by both positive subjective ratings and fewer transitions between the overview and individual items.

Extending Fitts' law to more than one dimension has been recognized as having important implications for HCI. In spite of the progress made over the years, however, it is still far from a resolved issue. Our work approaches this problem from the viewpoint of a configuration space, which has served as a useful conceptual framework for understanding human preference in perception. Notably, human are found to be biased towards regular configurations. In this work, we extended the configuration space framework to the domain of motor behavior, analyzed 2D pointing, and developed five models to account for the performance. An extensive experiment was conducted to measure the fit of the derived models and that of three previous models. Consistent with our hypothesis, the model reflecting a bias towards regular configuration was found to have the most satisfactory fit with the data. The paper concludes with discussions on improving understanding of Fitts' law and the implications for HCI.

The primary goal of the Midas project is to build a system that enables easy and scalable integration of unstructured and semi-structured information present across multiple data sources. As a first step in this direction, we have built a system that extracts and integrates information from regulatory filings submitted to the U.S. Securities and Exchange Commission (SEC) and the Federal Deposit Insurance Corporation (FDIC). Midas creates a repository of entities, events, and relationships by extracting, conceptualizing, integrating, and aggregating data from unstructured and semi-structured documents. This repository enables applications to use the extracted and integrated data in a variety of ways including mashups with other public data and complex risk analysis.

Abstract A survey of the 113 academic libraries of the Association of Research Libraries (ARL) was administered to investigate whether Web usability Policies/Standards/Guidelines (PSGs) are in place, the levels of difficulty surrounding implementation, the impact of PSGs on actual usability practice, e.g., testing, resources, etc., and the relationship between ARL ranking and usability practice or PSGs. The response rate was over 74%. Results show that 25 (30%) libraries have PSGs dedicated to Web usability. Seventy‐one (85%) libraries have conducted usability testing on their main Web sites, online public access catalogs (OPAC), or lower‐level pages. Nevertheless, only seven libraries performed iterative testing of these platforms at pre‐, during, and post‐design stages. Statistical analysis indicates that having PSGs does not affect the amount of usability testing performed or the resources available for library Web usability initiatives. In addition, ARL ranking has no or little impact on PSGs, testing, or resources.

We present DaNaLIX, a prototype domain-adaptive natural language interface for querying XML. Our system is an extension of NaLIX, a generic natural language interface for querying XML. While retaining the portability of a purely generic system like NaLIX, DaNaLIX can exploit domain knowledge, whenever available, to its advantage for query translation. More importantly, in DaNaLIX such domain knowledge does not have to be pre-defined; instead it can be automatically obtained from the interactions between a user and the system. In this demonstration, we describe the overall architecture of DaNaLIX. We also demonstrate how a generic system like DaNaLIX can take advantage of domain knowledge to improve its usability and query translation accuracy. In addition, we show DaNaLIX still possesses the portability of a generic system by using data collections from three different domains. Finally, we present how domain knowledge can be obtained through user interactions in an automatic fashion.

We describe the construction of a generic natural language query interface to an XML database. Our interface can accept a large class of English sentences as a query, which can be quite complex and include aggregation, nesting, and value joins, among other things. This query is translated, potentially after reformulation, into an XQuery expression. The translation is based on mapping grammatical proximity of natural language parsed tokens in the parse tree of the query sentence to proximity of corresponding elements in the XML data to be retrieved. Iterative search in the form of followup queries is also supported. Our experimental assessment, through a user study, demonstrates that this type of natural language interface is good enough to be usable now, with no restrictions on the application domain.

Database query languages can be intimidating to the non-expert, leading to the immense recent popularity for keyword based search in spite of its significant limitations. The holy grail has been the development of a natural language query interface. We present NaLIX, a generic interactive natural language query interface to an XML database. Our system can accept an arbitrary English language sentence as query input, which can include aggregation, nesting, and value joins, among other things. This query is translated, potentially after reformulation, into an XQuery expression that can be evaluated against an XML database. The translation is done through mapping grammatical proximity of natural language parsed tokens to proximity of corresponding elements in the result XML. In this demonstration, we show that NaLIX, while far from being able to pass the Turing test, is perfectly usable in practice, and able to handle even quite complex queries in a variety of application domains. In addition, we also demonstrate how carefully designed features in NaLIX facilitate the interactive query process and improve the usability of the interface.