Proceedings of the 31st ACM Conference on Hypertext and Social Media最新文献

{"title":"Analyzing the Effects of \"People also ask\" on Search Behaviors and Beliefs","authors":"Suppanut Pothirattanachaikul, Takehiro Yamamoto, Yusuke Yamamoto, Masatoshi Yoshikawa","doi":"10.1145/3372923.3404786","DOIUrl":"https://doi.org/10.1145/3372923.3404786","url":null,"abstract":"This study investigates the impact of collective questions and answers displayed on Search engine result pages (SERP), known as People also ask on searchers' behaviors and beliefs. Two experiments were conducted in which participants were asked to perform health-related search tasks. In both experiments, items in People also ask were manipulated. Experiment 1 focused on the effect of question, answer, and answer's opinion. Experiment 2 focused on the effect of the alternative question, i.e., a question related to the solution that can achieve the same goal as a query. The results revealed the following. (i) Participants issued fewer queries and spent less time on a SERP when People also ask were presented. (ii) Participants were less likely to interact with a SERP when they first encounter a belief-inconsistent answer. (iii) We could not confirm the effect of People also ask on beliefs at the current state. The findings suggest that People also ask might not help mitigate confirmation bias as participants are likely to spend less effort on the search process (i.e., issue fewer queries) when they first encounter a belief-inconsistent answer unlike when they encounter a belief-inconsistent document within the search results. An additional experiment is required to validate that participants who first encounter a belief-inconsistent answer are more likely to alter their beliefs as the number of such participants was inadequate.","PeriodicalId":389616,"journal":{"name":"Proceedings of the 31st ACM Conference on Hypertext and Social Media","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126923314","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Calibration in Collaborative Filtering Recommender Systems: a User-Centered Analysis","authors":"Kun-hsien Lin, Nasim Sonboli, B. Mobasher, R. Burke","doi":"10.1145/3372923.3404793","DOIUrl":"https://doi.org/10.1145/3372923.3404793","url":null,"abstract":"Recommender systems learn from past user preferences in order to predict future user interests and provide users with personalized suggestions. Previous research has demonstrated that biases in user profiles in the aggregate can influence the recommendations to users who do not share the majority preference. One consequence of this bias propagation effect is miscalibration, a mismatch between the types or categories of items that a user prefers and the items provided in recommendations. In this paper, we conduct a systematic analysis aimed at identifying key characteristics in user profiles that might lead to miscalibrated recommendations. We consider several categories of profile characteristics, including similarity to the average user, propensity towards popularity, profile diversity, and preference intensity. We develop predictive models of miscalibration and use these models to identify the most important features correlated with miscalibration, given different algorithms and dataset characteristics. Our analysis is intended to help system designers predict miscalibration effects and to develop recommendation algorithms with improved calibration properties.","PeriodicalId":389616,"journal":{"name":"Proceedings of the 31st ACM Conference on Hypertext and Social Media","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134613240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Date the Artist: A Virtual Date with a Virtual Character","authors":"Hanae Hmimid, M. Mosher","doi":"10.1145/3372923.3404803","DOIUrl":"https://doi.org/10.1145/3372923.3404803","url":null,"abstract":"Date the Artist is a video based interactive website that presents people with the opportunity to date a virtual character (VC). Each webpage represents a stage of the relationship. In each page, the user has 2 to 3 choices leading to different videos. By the end, all the videos lead to the same final video representing the end of the relationship. The goal of this paper is to explain the design process, the main metaphor behind the project, as well as highlighting the overall user experience.","PeriodicalId":389616,"journal":{"name":"Proceedings of the 31st ACM Conference on Hypertext and Social Media","volume":"50 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113957640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Personalizing Information Exploration with an Open User Model","authors":"Behnam Rahdari, Peter Brusilovsky, Dmitriy Babichenko","doi":"10.1145/3372923.3404797","DOIUrl":"https://doi.org/10.1145/3372923.3404797","url":null,"abstract":"Over the past two decades, several information exploration approaches were suggested to support a special category of search tasks known as exploratory search. These approaches creatively combined search, browsing, and information analysis steps shifting user efforts from recall (formulating a query) to recognition (i.e., selecting a link) and helping them to gradually learn more about the explored domain. More recently, a few projects demonstrated that personalising the process of information exploration with models of user interests can add value to information exploration systems. However, the current model-based information exploration interfaces are very sophisticated and focus on highly experienced users. The project presented in this paper attempted to assess the value of open user modeling in supporting personalized information exploration by novice users. We present an information exploration system with an open and controllable user model, which supports undergraduate students in finding research advisors. A controlled study of this system with target users demonstrated its advantage over a traditional search interface and revealed interesting aspects of user behavior in a model-based interface.","PeriodicalId":389616,"journal":{"name":"Proceedings of the 31st ACM Conference on Hypertext and Social Media","volume":"46 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116394088","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Keeping People Playing: The Effects of Domain News Presentation on Player Engagement in Educational Prediction Games","authors":"Gabriel S. Dzodom, Akshay Kulkarni, C. Marshall, F. Shipman","doi":"10.1145/3372923.3404813","DOIUrl":"https://doi.org/10.1145/3372923.3404813","url":null,"abstract":"Educational prediction games use the popularity and engagement of fantasy sports as a success model to promote learning in other domains. Fantasy sports motivate players to stay up-to-date with relevant news and explore large statistical data sets, thereby deepening their domain understanding while potentially honing their data analysis skills. We conducted a study of fantasy sports players, and discovered that while some participants performed sophisticated data analysis to support their gameplay, far more relied on news and published commentary. We used results from this study to design a prototype prediction game, Fantasy Climate, which helps players move from intuitions and advice to consuming news and analyzing data by supporting a variety of activities essential to gameplay. Because news is a key component of Fantasy Climate, we evaluated two link-based interfaces to domain-related news, one geospatial and the other organized as a list. The evaluation revealed that news presentation has a strong effect on players' engagement and performance: players using the geospatial interface not only were more engaged in the game; they also made better predictions than players who used the list-based presentation.","PeriodicalId":389616,"journal":{"name":"Proceedings of the 31st ACM Conference on Hypertext and Social Media","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130226639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Matching User Preferences and Behavior for Mobility","authors":"Silvia Basile, Cristian Consonni, Matteo Manca, Ludovico Boratto","doi":"10.1145/3372923.3404839","DOIUrl":"https://doi.org/10.1145/3372923.3404839","url":null,"abstract":"Understanding user mobility is central to develop better transport systems that answer users' needs. Users usually plan their travel according to their needs and preferences; however, different factors can influence their choices when traveling. In this work, we model users' preferences, and we match their actual transport use. We use data coming from a mobility platform developed for mobile devices, whose aim is to understand the value of users' travel time. Our first goal is to characterize the perception that users have of their mobility by analyzing their general preferences expressed before their travel time. Our approach combines dimensionality reduction and clustering techniques to provide interpretable profiles of users. Then, we perform the same task after monitoring users' travels by doing a matching between users' preferences and their actual behavior. Our results show that there are substantial differences between users' perception of their mobility and their actual behavior: users overestimate their preferences for specific mobility modes, that in general, yield a lower return in terms of the worthwhileness of their trip.","PeriodicalId":389616,"journal":{"name":"Proceedings of the 31st ACM Conference on Hypertext and Social Media","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127111265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"What Authors Think about Hypertext Authoring","authors":"Sofia Kitromili, J. Jordan, D. Millard","doi":"10.1145/3372923.3404798","DOIUrl":"https://doi.org/10.1145/3372923.3404798","url":null,"abstract":"Despite significant research into authoring tools for interactive narratives and a number of established authoring platforms, there is still a lack of understanding around the authoring process itself, and the challenges that authors face when writing hypertext and other forms of interactive narratives. This has led to a monolithic view of authoring, which has hindered tool design, resulting in tools that can lack focus, or ignore important parts of the creative process. In order to understand how authors practise writing, we conducted semi-structured interviews with 20 interactive narrative authors. Using a qualitative analysis, we coded their comments to identify both processes and challenges, and then mapped these against each other in order to understand where issues occurred during the authoring process. In our previous work we were able to gather together a set of authoring steps that were relevant to interactive narratives through a review of the academic literature. Those steps were: Training/Support, Planning, Visualising/Structuring, Writing, Editing, and Compiling/Testing. In this work we discovered two additional authoring steps, Ideation and Publishing that had not been previously identified in our reviews of the academic literature - as these are practical concerns of authors that are invisible to researchers. For challenges we identified 18 codes under 5 themes, falling into 3 phases of development: Pre-production, where issues fall under User/Tool Misalignment and Documentation; Production, adding issues under Complexity and Programming Environment; and Post-production, replacing previous issues with longer term issues related to the narrative's Lifecycle. Our work shows that the authoring problem goes beyond the technical difficulties of using a system, rather it is rooted in the common misalignment between the authors' expectations and the tools capabilities, the fundamental tension between expressivity and complexity, and the invisibility of the edges of the process to researchers and tool builders. Our work suggests that a less monolithic view of authoring would allow designers to create more focused tools and address issues specifically at the places in which they occur.","PeriodicalId":389616,"journal":{"name":"Proceedings of the 31st ACM Conference on Hypertext and Social Media","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124501040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Knowledge-infused Deep Learning","authors":"Manas Gaur, Ugur Kursuncu, A. Sheth, Ruwan Wickramarachchi, S. Yadav","doi":"10.1145/3372923.3404862","DOIUrl":"https://doi.org/10.1145/3372923.3404862","url":null,"abstract":"Deep Learning has shown remarkable success during the last decade for essential tasks in computer vision and natural language processing. Yet, challenges remain in the development and deployment of artificial intelligence (AI) models in real-world cases, such as dependence on extensive data and trust, explainability, traceability, and interactivity. These challenges are amplified in high-risk fields, including healthcare, cyber threats, crisis response, autonomous driving, and future manufacturing. On the other hand, symbolic computing with knowledge graphs has shown significant growth in specific tasks with reliable performance. This tutorial (a) discusses the novel paradigm of knowledge-infused deep learning to synthesize neural computing with symbolic computing (b) describes different forms of knowledge and infusion methods in deep learning, and (c) discusses application-specific evaluation methods to assure explainability and reasoning using benchmark datasets and knowledge-resources. The resulting paradigm of \"knowledge-infused learning'' combines knowledge from both domain expertise and physical models. A wide variety of techniques involving shallow, semi-deep, and deep infusion will be discussed along with the corresponding intuitions, limitations, use cases, and applications. More details can be found urlhttp://kidl2020.aiisc.ai/.","PeriodicalId":389616,"journal":{"name":"Proceedings of the 31st ACM Conference on Hypertext and Social Media","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124590724","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Noise-Enhanced Community Detection","authors":"Reyhaneh Abdolazimi, Shengmin Jin, R. Zafarani","doi":"10.1145/3372923.3404788","DOIUrl":"https://doi.org/10.1145/3372923.3404788","url":null,"abstract":"Community structure plays a significant role in uncovering the structure of a network. While many community detection algorithms have been introduced, improving the quality of detected communities is still an open problem. In many areas of science, adding noise improves system performance and algorithm efficiency, motivating us to also explore the possibility of adding noise to improve community detection algorithms. We propose a noise-enhanced community detection framework that improves communities detected by existing community detection methods. The framework introduces three noise methods to help detect communities better. Theoretical justification and extensive experiments on synthetic and real-world datasets show that our framework helps community detection methods find better communities.","PeriodicalId":389616,"journal":{"name":"Proceedings of the 31st ACM Conference on Hypertext and Social Media","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115835458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Anonymity Effects: A Large-Scale Dataset from an Anonymous Social Media Platform","authors":"Mainack Mondal, D. Correa, Fabrício Benevenuto","doi":"10.1145/3372923.3404792","DOIUrl":"https://doi.org/10.1145/3372923.3404792","url":null,"abstract":"Today online social media sites function as the medium of expression for billions of users. As a result, aside from conventional social media sites like Facebook and Twitter, platform designers introduced many alternative social media platforms (e.g., 4chan, Whisper, Snapchat, Mastodon) to serve specific userbases. Among these platforms, anonymous social media sites like Whisper and 4chan hold a special place for researchers. Unlike conventional social media sites, posts on anonymous social media sites are not associated with persistent user identities or profiles. Thus, these anonymous social media sites can provide an extremely interesting data-driven lens into the effects of anonymity on online user behavior. However, to the best of our knowledge, currently there are no publicly available datasets to facilitate research efforts on these anonymity effects. To that end, in this paper, we aim to publicly release the first ever large-scale dataset from Whisper, a large anonymous online social media platform. Specifically, our dataset contains 89.8 Million Whisper posts (called \"whispers'') published between a 2-year period from June 6, 2014 to June 6, 2016 (when Whisper was quite popular). Each of these whispers contained both post text and associated metadata. The metadata contains information like coarse-grained location of upload and categories of whispers. We also present preliminary descriptive statistics to demonstrate a significant language and categorical diversity in our dataset. We leverage previous work as well as novel analysis to demonstrate that the whispers contain personal emotions and opinions (likely facilitated by a disinhibition complex due to anonymity). Consequently, we envision that our dataset will facilitate novel research ranging from understanding online aggression to detect depression within online populace.","PeriodicalId":389616,"journal":{"name":"Proceedings of the 31st ACM Conference on Hypertext and Social Media","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124235399","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}