AI has great potential to transform education and daily life. However, before integrating AI into classrooms, it is crucial to first educate children on what AI is and how to use it responsibly. Effective AI education should build on children's existing perceptions, address misconceptions, and establish a solid foundation for AI literacy. This study explores primary school students’ perception of AI and its relationship to their demographic characteristics and digital skills. A survey was conducted in seven local schools, with 233 students participating. The results indicate that most of them were unfamiliar with AI, and those who attempted to define or depict it often associated it with robots or digital devices. The study also found significant differences in students’ AI perceptions based on factors like gender, grade, and prior digital skills training. These variables were also linked to students’ awareness and understanding of AI. These findings underscore the need for targeted AI educational interventions for primary school students, leveraging their existing perceptions.

As AI technologies grow more influential in shaping modern life, there is an urgent need to make AI literacy accessible beyond academic and technical communities. This paper presents the design, delivery, and evaluation of an online AI course targeting the general public. The course combined asynchronous lectures, interactive live sessions, and reflective assignments. Of the 343 people who registered, 169 completed the program. Using validated instruments administered before and after the course, we measured changes in participants’ attitudes toward AI and their AI literacy. Our findings revealed statistically significant changes in AI literacy, specifically in awareness, usage, and evaluation constructs, as well as a rise in positive attitudes toward AI. High satisfaction scores and qualitative feedback further support the course’s effectiveness. These findings reinforce the importance of inclusive, scalable educational interventions for empowering the public to navigate AI technologies.

Educational tools are increasingly used to introduce AI to children. However, there are few tools co-designed with teachers that aim to tackle the misconceptions children have about AI. This paper presents the results of a participatory design process aimed at creating educational tools that help primary school students develop AI literacy by addressing misconceptions of AI. Our two-phase process began with a workshop in which teachers were introduced to misconceptions children hold about AI and invited to co-design mock-ups for tools to address one of these misconceptions. Building on teachers' designs, we developed a prototype comprising three games that address the misconception that ''AI is always right.'' We then conducted two evaluation studies, one with the workshop participants and one crowdsourcing survey with primary school teachers. By analyzing survey responses, we examine teachers' …

Teens are increasingly interacting with AI systems in their everyday lives, yet many have a limited understanding of how these technologies function or what their limitations are. This highlights the need for early AI education. To create effective learning programs, it is crucial first to explore how teens perceive AI. This study examines the perceptions of middle school students about AI and their level of AI literacy, while also analyzing how factors such as demographics, attitudes, and prior training in digital skills influence these perceptions. Our findings show that students commonly view AI as tools or programs that deliver information or answers. Overall, participants demonstrated a moderate level of AI literacy and generally held neutral attitudes toward AI. Notably, gender, grade level, and digital skills training emerged as key influences on both AI literacy and perceptions. Furthermore, student attitudes, both positive and negative, were significantly associated with their level of AI literacy, with marked differences observed based on gender and previous exposure to training in digital skills.

The KeepA(n)I platform facilitates the auditing of computer vision systems that tag images, which aid visual communication on the Web and social media, from content moderation to the development of new apps and tools. In particular, KeepA(n)I enables a broad set of stakeholders to scrutinize a process of interest that embeds an image tagger for issues of social stereotyping, while also examining the social norms that humans apply to the observed AI behaviors. KeepA(n)I’s approach, and its use of the power of the crowd, can aid the stakeholders in receiving responses to both descriptive and normative questions (i.e., which stereotyping behaviors are observed and if they are considered problematic by a given “crowd” for an intended context). We provide an overview of the platform, its key features, and a discussion via a use case on the diverse set of stakeholders that can benefit from it.

We all interact with AI daily, however, our understanding of it often remains limited. We present a training conducted as part of an Erasmus YE, with 36 individuals aged 18 to 30 from Austria, Armenia, Bulgaria, Latvia, Poland and Portugal. Our findings indicate that participants improved their AI literacy and recognized the value of such training, expressing that AI training is useful for everyone.

In today’s world, children are increasingly interacting with AI technologies as part of their daily routines. However, many children may not fully grasp how these technologies function or their implications. Misconceptions about AI capabilities, risks, and benefits abound, underlining the importance of early education on the subject. Designing educational tools and materials tailored for children necessitates a deep understanding of their existing knowledge and perceptions of AI. By leveraging children’s insights and experiences with AI, we can develop effective educational strategies that cater to their specific needs and enhance their understanding of this rapidly evolving technology.

Crowdsourcing plays an important role in Web and social media research, from data annotation, to online experiments and user surveys. With the emergence of Generative AI (GenAI), researchers are considering how models and tools such as GPT might replace crowdwork. Many have already evaluated GPT on annotation tasks. However, it is less clear how GenAI might impact other types of tasks, or to what extent crowdworkers have already incorporated it into their work processes. Thus, we asked crowdworkers directly regarding their use of GenAI, via a survey at two points in time, across three commercial platforms. We found evidence that workers' self-reported use of GenAI did not change over time, but rather, was strongly correlated to the platform in which they operate, with MTurk workers using GenAI much more often than those operating at Clickworker and Prolific. As most respondents reported that survey completion is their "usual type of task", we discuss the implication of the use of GenAI in user surveys, via specific examples of ICWSM research.

With the surge in data-centric AI and its increasing capabilities, AI applications have become a part of our everyday lives. However, misunderstandings regarding their capabilities, limitations, and associated advantages and disadvantages are widespread. Consequently, in the university setting, there is a crucial need to educate not only computer science majors but also students from various disciplines about AI. In this experience report, we present an overview of an introductory course that we offered to students coming from different majors. Moreover, we discuss the assignments and quizzes of the course, which provided students with a firsthand experience of AI processes and insights into their learning patterns. Additionally, we provide a summary of the course evaluation, as well as students' performance. Finally, we present insights gained from teaching this course and elaborate on our future plans.

At the end of October 2022, Elon Musk concluded his acquisition of Twitter. In the weeks and months before that, several questions were publicly discussed that were not only of interest to the platform's future buyers, but also of high relevance to the Computational Social Science research community. For example, how many active users does the platform have? What percentage of accounts on the site are bots? And, what are the dominating topics and sub-topical spheres on the platform? In a globally coordinated effort of 80 scholars to shed light on these questions, and to offer a dataset that will equip other researchers to do the same, we have collected all 375 million tweets published within a 24-hour time period starting on September 21, 2022. To the best of our knowledge, this is the first complete 24-hour Twitter dataset that is available for the research community. With it, the present work aims to accomplish two goals. First, we seek to answer the aforementioned questions and provide descriptive metrics about Twitter that can serve as references for other researchers. Second, we create a baseline dataset for future research that can be used to study the potential impact of the platform's ownership change.

With the rise of data-driven AI and its "democratization", we are all interacting with AI-enabled technologies in everyday life. However, not everyone understands how these technologies work. There are many misconceptions surrounding what they can and cannot do, and what are the risks and benefits. Thus, there is a need to educate the general public about everyday AI, upscaling their algorithmic literacy and helping them become more informed, responsible users. We describe the development and evaluation of an eight-week course open to the public, AI in Everyday Life. Pre- and post-course questionnaires were used to evaluate the impact of the course and participants' attitudes towards AI applications. The results suggest that more targeted educational approaches are needed for the general public to fully understand the strengths and weaknesses of the use of AI-enabled technologies.

It is increasingly easy for interested parties to play a role in the development of predictive algorithms, with a range of available tools and platforms for building datasets, as well as for training and evaluating machine learning (ML) models. For this reason, it is essential to create awareness among practitioners on the ethical challenges, such as the presence of social bias in training data. We present RECANT (Raising Awareness of Social Bias in Crowdsourced Training Data), a tool that allows users to explore the behaviors of four biometric models -- predicting the gender and race, as well as the perceived attractiveness and trustworthiness, of the person depicted in an input image. These models have been trained on a crowdsourced dataset of passport-style people images, where crowd annotators described attributes of the images, and reported their own demographic characteristics. With RECANT, users can explore the correct and wrong predictions made by each model, when using different subsets of the data in training, based on annotator attributes. We present its features, along with sample exercises, as a hands-on tool for raising awareness of potential pitfalls in data practices surrounding ML.

Following the literature on dehumanization via technology, we audit six proprietary image tagging algorithms (ITAs) for their potential to perpetuate dehumanization. We examine the ITAs' outputs on a controlled dataset of images depicting a diverse group of people for tags that indicate the presence of a human in the image. Through an analysis of the (mis)use of these tags, we find that there are some individuals whose 'humanness' is not recognized by an ITA, and that these individuals are often from marginalized social groups. Finally, we compare these findings with the use of the 'face' tag, which can be used for surveillance, revealing that people's faces are often recognized by an ITA even when their 'humanness' is not. Overall, we highlight the subtle ways in which ITAs may inflict widespread, disparate harm, and emphasize the importance of considering the social context of the resulting application.

Data attained through crowdsourcing have an essential role in the development of computer vision algorithms. Crowdsourced data might include reporting biases, since crowdworkers usually describe what is “worth saying” in addition to images’ content. We explore how the unprecedented events of 2020, including the unrest surrounding racial discrimination, and the COVID-19 pandemic, might be reflected in responses to an open-ended annotation task on people images, originally executed in 2018 and replicated in 2020. Analyzing themes of Identity and Health conveyed in workers’ tags, we find evidence that supports the potential for temporal sensitivity in crowdsourced data. The 2020 data exhibit more race-marking of images depicting non-Whites, as well as an increase in tags describing Weight. We relate our findings to the emerging research on crowdworkers’ moods. Furthermore, we discuss the implications of (and suggestions for) designing tasks on proprietary platforms, having demonstrated the possibility for additional, unexpected variation in crowdsourced data due to significant events.

Professionals are increasingly relying on algorithmic systems for decision making however, algorithmic decisions occasionally perceived as biased or not just. Prior work has provided evidences that education can make a difference on the perception of young developers on algorithmic fairness. In this paper, we investigate computer science students' perception of FATE in algorithmic decision-making and whether their views on FATE can be changed by attending a seminar on FATE topics. Participants attended a seminar on FATE in algorithmic decision-making and they were asked to respond to two online questionnaires to measure their pre- and post-seminar perception on FATE. Results show that a short seminar can make a difference in understanding and perception as well as the attitude of the students towards FATE in algorithmic decision support. CS curricula need to be updated and include FATE topics if we want algorithmic decision support systems to be just for all.

During times of crisis, information access is crucial. Given the opaque processes behind modern search engines, it is important to understand the extent to which the "picture" of the Covid-19 pandemic accessed by users differs. We explore variations in what users "see" concerning the pandemic through Google image search, using a two-step approach. First, we crowdsource a search task to users in four regions of Europe, asking them to help us create a photo documentary of Covid-19 by providing image search queries. Analysing the queries, we find five common themes describing information needs. Next, we study three sources of variation - users' information needs, their geo-locations and query languages - and analyse their influences on the similarity of results. We find that users see the pandemic differently depending on where they live, as evidenced by the 46% similarity across results. When users expressed a given query in different languages, there was no overlap for most of the results. Our analysis suggests that localisation plays a major role in the (dis)similarity of results, and provides evidence of the diverse "picture" of the pandemic seen through Google.

The series of FAT/FAccT events aim at bringing together researchers and practitioners interested in fairness, accountability, transparency and ethics of computational methods. The FATE/MM workshop focuses on addressing these issues in the Multimedia field. Multimedia computing technologies operate today at an unprecedented scale, with a growing community of scientists interested in multimedia models, tools and applications. Such continued growth has great implications not only for the scientific community, but also for the society as a whole. Typical risks of large-scale computational models include model bias and algorithmic discrimination. These risks become particularly prominent in the multimedia field, which historically has been focusing on user-centered technologies. To ensure a healthy and constructive development of the best multimedia technologies, this workshop offers a space to discuss how to develop ethical, fair, unbiased, representative, and transparent multimedia models, bringing together researchers from different areas to present computational solutions to these issues.

The 3rd FairUMAP workshop brings together researchers working at the intersection of user modeling, adaptation, and personalization on the one hand, and bias, fairness and transparency in algorithmic systems on the other hand.

Machine-learned computer vision algorithms for tagging images are increasingly used by developers and researchers, having become popularized as easy-to-use "cognitive services." Yet these tools struggle with gender recognition, particularly when processing images of women, people of color and non-binary individuals. Socio-technical researchers have cited data bias as a key problem; training datasets often over-represent images of people and contexts that convey social stereotypes. The social psychology literature explains that people learn social stereotypes, in part, by observing others in particular roles and contexts, and can inadvertently learn to associate gender with scenes, occupations and activities. Thus, we study the extent to which image tagging algorithms mimic this phenomenon. We design a controlled experiment, to examine the interdependence between algorithmic recognition of context and the depicted person's gender. In the spirit of auditing to understand machine behaviors, we create a highly controlled dataset of people images, imposed on gender-stereotyped backgrounds. Our methodology is reproducible and our code publicly available. Evaluating five proprietary algorithms, we find that in three, gender inference is hindered when a background is introduced. Of the two that "see" both backgrounds and gender, it is the one whose output is most consistent with human stereotyping processes that is superior in recognizing gender. We discuss the accuracy--fairness trade-off, as well as the importance of auditing black boxes in better understanding this double-edged sword.

Crowdsourcing plays a key role in developing algorithms for image recognition or captioning. Major datasets, such as MS COCO or Flickr30K, have been built by eliciting natural language descriptions of images from workers. Yet such elicitation tasks are susceptible to human biases, including stereotyping people depicted in images. Given the growing concerns surrounding discrimination in algorithms, as well as in the data used to train them, it is necessary to take a critical look at this practice. We conduct experiments at Figure Eight using a controlled set of people images. Men and women of various races are positioned in the same manner, wearing a grey t-shirt. We prompt workers for 10 descriptive labels, and consider them using the human-centric approach, which assumes reporting bias. We find that “what’s worth saying” about these uniform images often differs as a function of the gender and race of the depicted person, violating the notion of group fairness. Although this diversity in natural language people descriptions is expected and often beneficial, it could result in automated disparate impact if not managed properly.

Abstract Image recognition algorithms that automatically tag or moderate content are crucial in many applications but are increasingly opaque. Given transparency concerns, we focus on understanding how algorithms tag people images and their inferences on attractiveness. Theoretically, attractiveness has an evolutionary basis, guiding mating behaviors, although it also drives social behaviors. We test image-tagging APIs as to whether they encode biases surrounding attractiveness. We use the Chicago Face Database, containing images of diverse individuals, along with subjective norming data and objective facial measurements. The algorithms encode biases surrounding attractiveness, perpetuating the stereotype that “what is beautiful is good.” Furthermore, women are often misinterpreted as men. We discuss the algorithms’ reductionist nature, and their potential to infringe on users’ autonomy and well-being, as well as the ethical and legal considerations for developers. Future services should monitor algorithms’ behaviors given their prevalence in the information ecosystem and influence on media.

Image analysis algorithms have been a boon to personalization in digital systems and are now widely available via easy-to-use APIs. However, it is important to ensure that they behave fairly in applications that involve processing images of people, such as dating apps. We conduct an experiment to shed light on the factors influencing the perception of "fairness." Participants are shown a photo along with two descriptions (human- and algorithm-generated). They are then asked to indicate which is "more fair" in the context of a dating site, and explain their reasoning. We vary a number of factors, including the gender, race and attractiveness of the person in the photo. While participants generally found human-generated tags to be more fair, API tags were judged as being more fair in one setting - where the image depicted an "attractive," white individual. In their explanations, participants often mention accuracy, as well as the objectivity/subjectivity of the tags in the description. We relate our work to the ongoing conversation about fairness in opaque tools like image tagging APIs, and their potential to result in harm.

Human computation is often subject to systematic biases. We consider the case of linguistic biases and their consequences for the words that crowdworkers use to describe people images in an annotation task. Social psychologists explain that when describing oth- ers, the subconscious perpetuation of stereotypes is in- evitable, as we describe stereotype-congruent people and/or in-group members more abstractly than others. In an MTurk experiment we show evidence of these bi- ases, which are exacerbated when an image’s “popular tags” are displayed, a common feature used to provide social information to workers. Underscoring recent calls for a deeper examination of the role of training data quality in algorithmic biases, results suggest that it is rather easy to sway human judgment.

There is growing evidence that search engines produce results that are socially biased, reinforcing a view of the world that aligns with prevalent social stereotypes. One means to promote greater transparency of search algorithms - which are typically complex and proprietary - is to raise user awareness of biased result sets. However, to date, little is known concerning how users perceive bias in search results, and the degree to which their perceptions differ and/or might be predicted based on user attributes. One particular area of search that has recently gained attention, and forms the focus of this study, is image retrieval and gender bias. We conduct a controlled experiment via crowdsourcing using participants recruited from three countries to measure the extent to which workers perceive a given image results set to be subjective or objective. Demographic information about the workers, along with measures of sexism, are gathered and analysed to investigate whether (gender) biases in the image search results can be detected. Amongst other findings, the results confirm that sexist people are less likely to detect and report gender biases in image search results.

There is much concern about algorithms that underlie information services and the view of the world they present. We develop a novel method for examining the content and strength of gender stereotypes in image search, inspired by the trait adjective checklist method. We compare the gender distribution in photos retrieved by Bing for the query "person" and for queries based on 68 character traits (e.g., "intelligent person") in four regional markets. Photos of men are more often retrieved for "person," as compared to women. As predicted, photos of women are more often retrieved for warm traits (e.g., "emotional") whereas agentic traits (e.g., "rational") are represented by photos of men. A backlash effect, where stereotype-incongruent individuals are penalized, is observed. However, backlash is more prevalent for "competent women" than "warm men." Results underline the need to understand how and why biases enter search algorithms and at which stages of the engineering process.

Gender stereotypes are strong influences on human behavior. Given our tendency to anthropomorphize, incorporating gender cues into a robot's design can influence acceptance by humans. However, little is known about the interaction between human and robot gender. We focus on the role of gender in eliciting negative, ``uncanny" reactions from observers. We create a corpus of YouTube videos featuring robots with female, male and no gender cues. Our experiment is grounded in Gray and Wegner's (2012) model, which holds that uncanny reactions are driven by the perception of robot agency (i.e., ability to plan and control) and experience (i.e., ability to feel), which in turn, is driven by robot appearance and behavior. Participants watched videos and completed questionnaires to gauge perceptions of robots as well as affective reactions. We used Structural Equation Modeling to test whether the model explains reactions of both men and women. For gender-neutral robots, it does. However, we find a salient human-robot gender interaction. Men's uncanny reactions to robots with female cues are best predicted by the perception of experience, while women's negativity toward masculine robots is driven by perceived agency. The result is interpreted in light of the ``Big Two" dimensions of person perception, which underlie expectations for women to be warm and men to be agentic. When a robot meets these expectations, it increases the chances of an uncanny reaction in the other-gender observer.

Linguistic mimicry, the adoption of another’s language patterns, is a subconscious behavior with pro-social benefits. However, some professions advocate its conscious use in empathic communication. This involves mutual mimicry; effective communicators mimic their interlocutors, who also mimic them back. Since mimicry has often been studied in face-to-face contexts, we ask whether individuals with empathic dispositions have unique communication styles and/or elicit mimicry in mediated communication on Facebook. Participants completed Davis’s Interpersonal Reactivity Index and provided access to Facebook activity. We confirm that dispositional empathy is correlated to the use of particular stylistic features. In addition, we identify four empathy profiles and find correlations to writing style. When a linguistic feature is used, this often “triggers” use by friends. However, the presence of particular features, rather than participant disposition, best predicts mimicry. This suggests that machine-human communications could be enhanced based on recently used features, without extensive user profiling.

Games with a Purpose (GWAP) is a popular approach for metadata creation, enabling institutions to collect descriptions of digital artifacts on a mass scale. Creating metadata is challenging not only because one must recognize the artifact; the description must then be encoded into natural language. Language behaviors are influenced by many social factors, particularly when we are asked to describe other people. We consider labels for images of people generated via the ESP Game. While ESP has been shown to produce relevant labels, critics claim they are obvious and stereotypical. Based on theories of linguistic biases, we examine whether there are systematic differences in the ways players describe images of men versus women. Our first analysis considers images of people generally, and reveals a tendency for women to be described with subjective adjectives. A second analysis compares images depicting men and women within each of six occupational roles. Images of women receive more labels related to appearance, whereas those depicting men receive more occupation-related labels. Our work exposes the presence of gender-based stereotypes through linguistic biases, illustrates the forms in which they manifest, and raises important implications for those who design systems or train algorithms using data produced via GWAP.

As Twitter becomes a more common means for officials to communicate with their constituents, it becomes more important that we understand how officials use these communication tools. Using data from 380 members of Congress' Twitter activity during the winter of 2012, we find that officials frequently use Twitter to advertise their political positions and to provide information but rarely to request political action from their constituents or to recognize the good work of others. We highlight a number of differences in communication frequency between men and women, Senators and Representatives, Republicans and Democrats. We provide groundwork for future research examining the behavior of public officials online and testing the predictive power of officials' social media behavior.

Women and men communicate differently in both face-to-face and computer-mediated environments. We study linguistic patterns considered gendered in reviews contributed to the Internet Movie Database. IMDb has been described as a male-majority community, in which females contribute fewer reviews and enjoy less prestige than males. Analyzing reviews posted by prolific males and females, we hypothesize that females adjust their communication styles to be in sync with their male counterparts. We find evidence that while certain characteristics of "female language" persevere over time (e.g., frequent use of pronouns) others (e.g., hedging) decrease with time. Surprisingly, we also find that males often increase their use of "female" features. Our results indicate, that even when they resemble men's reviews linguistically, women's reviews still enjoy less prestige and smaller audiences.

Classic news summarization plays an important role with the exponential document growth on the Web. Many approaches are proposed to generate summaries but seldom simultaneously consider evolutionary characteristics of news plus to traditional summary elements. Therefore, we present a novel framework for the web mining problem named Evolutionary Timeline Summarization (ETS). Given the massive collection of time-stamped web documents related to a general news query, ETS aims to return the evolution trajectory along the timeline, consisting of individual but correlated summaries of each date, emphasizing relevance, coverage, coherence and cross-date diversity. ETS greatly facilitates fast news browsing and knowledge comprehension and hence is a necessity. We formally formulate the task as an optimization problem via iterative substitution from a set of sentences to a subset of sentences that satisfies the above requirements, balancing coherence/diversity measurement and local/global summary quality. The optimized substitution is iteratively conducted by incorporating several constraints until convergence. We develop experimental systems to evaluate on 6 instinctively different datasets which amount to 10251 documents. Performance comparisons between different system-generated timelines and manually created ones by human editors demonstrate the effectiveness of our proposed framework in terms of ROUGE metrics.

Despite differences in the way that men and women experience goods and communicate their perspectives, online review communities typically do not provide participants' gender. We propose to infer author gender, given a set of reviews of a particular item, and experiment on reviews posted at the Internet Movie Database (IMDb). Using logistic regression, we explore the contribution of three types of information: 1) style, 2) content, and 3) metadata (e.g. review age, social feedback). Our results concur with previous research, in that there are salient differences in writing style and content between reviews authored by men versus women. However, in comparison to literary or scientific texts, to which classification tasks are often applied, reviews are brief and occur within the context of an ongoing discourse. Therefore, to compensative for the brevity of reviews, content and stylistic features can be augmented with metadata. We find in particular that the perceived utility of a review is an important correlate of gender. The model incorporating all features has a classification accuracy of 73.7% and is not as sensitive to review length as are those based only on stylistic or content features.

Online communities displaying textual postings require measures to combat information overload. One popular approach is to ask participants whether or not messages are helpful in order to then guide others to interesting content. Adopting a well-established framework for assessing data quality, we examine the nature of "helpfulness."We study consumer reviews at Amazon.com, deriving 22 measures quantifying their textual properties, authors' reputations and product characteristics. Confirmatory factor analysis reveals five underlying quality dimensions representing reviewers' reputations in the community, the topical relevancy of the reviews, the ease of understanding them, their believability and objectivity. A correlation and regression analysis confirms that these dimensions are related to the helpfulness scores assigned by community participants. However, it also uncovers a strong relationship between the chronological ordering of reviews and helpfulness, which both community participants and designers should keep in mind when using this method of social navigation.

Methods for detecting sentences in an input document set, which are both relevant and novel with respect to an information need, would be of direct benefit to many systems, such as extractive text summarizers. However, satisfactory levels of agreement between judges performing this task manually have yet to demonstrated, leaving researchers to conclude that the task is too subjective. In previous experiments, judges were asked to first identify sentences that are relevant to a general topic, and then to eliminate sentences from the list that do not contain new information. Currently, a new task is proposed, in which annotators perform the same procedure, but within the context of a specific, factual information need. In the experiment, satisfactory levels of agreement between independent annotators were achieved on the first step of identifying sentences containing relevant information relevant. However, the results indicate that judges do not agree on which sentences contain novel information.

We present an evaluation of a novel hierarchical text summarization method that allows users to view summaries of Web documents from small, mobile devices. Unlike previous approaches, ours does not require the documents to be in HTML since it infers a hierarchical structure automatically. Currently, the method is used to summarize news articles sent to a Web mail account in plain text format. Subjects used a Web-enabled mobile phone emulator to access the account's inbox and view the summarized news articles. They then used the summaries to complete several information-seeking tasks, which involved answering factual questions about the stories. In comparing the hierarchical text summary setting to that in which subjects were given the full text articles, there was no significant difference in task accuracy or the time taken to complete the task. However, in the hierarchical summarization setting, the number of bytes transferred per user request is less than half that of the full text case. Finally, in comparing the new method to three other summarization methods, subjects achieved significantly better accuracy on the tasks when using hierarchical summaries.

We present WAP MEAD, a WAP-enabled text summarization system. It incorporates a state-of-the art text summarizer enhanced to produce hierarchical summaries that are appropriate for various types of mobile devices, including cellular phones.

Multi-document discoure analysis has emerged with the potential of improving various information retrieval applications. Based on the newly proposed Cross-document Structure Theory (CST), this paper describes an empirical study that uses boosting to classify CST relationships between sentence pairs extracted from topically related documents. We show that the binary classifier for determining existence of structural relationships significantly outperforms the baseline. We also achieve promising results on the multi-class case in which the full taxonomy of relationships are considered.