Pub Date : 2021-09-25DOI: 10.1609/icwsm.v2i1.18630
F. Abel, M. Frank, N. Henze, D. Krause, Patrick Siehndel
The GroupMe! system provides a novel approach to social bookmarking. It enables users to create groups of arbitrary multimedia web resources and visualizes resources according to their media type. Therewith, content of a resource can be grasped immediately. Hence, GroupMe! groups form web sites -- comparable to Wikipedia pages -- that users visit in order to gather information about corresponding topics. Technically, the grouping of resources carries valuable information about web resources and their relations, and can be exploited to improve the mining of web content, e.g. for search and retrieval. GroupMe! is available via http://groupme.org.
{"title":"GroupMe! - Combining Ideas of Wikis, Social Bookmarking, and Blogging","authors":"F. Abel, M. Frank, N. Henze, D. Krause, Patrick Siehndel","doi":"10.1609/icwsm.v2i1.18630","DOIUrl":"https://doi.org/10.1609/icwsm.v2i1.18630","url":null,"abstract":"The GroupMe! system provides a novel approach to social bookmarking. It enables users to create groups of arbitrary multimedia web resources and visualizes resources according to their media type. Therewith, content of a resource can be grasped immediately. Hence, GroupMe! groups form web sites -- comparable to Wikipedia pages -- that users visit in order to gather information about corresponding topics. Technically, the grouping of resources carries valuable information about web resources and their relations, and can be exploited to improve the mining of web content, e.g. for search and retrieval. GroupMe! is available via http://groupme.org.","PeriodicalId":338112,"journal":{"name":"Proceedings of the International AAAI Conference on Web and Social Media","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128247199","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}
Pub Date : 2021-09-25DOI: 10.1609/icwsm.v2i1.18606
Mikhail Bautin, Lohit Vijayarenu, S. Skiena
There is a growing interest in mining opinions using sentiment analysis methods from sources such as news, blogs and product reviews. Most of these methods have been developed for English and are difficult to generalize to other languages. We explore an approach utilizing state-of-the-art machine translation technology and perform sentiment analysis on the English translation of a foreign language text. Our experiments indicate that (a) entity sentiment scores obtained by our method are statistically significantly correlated across nine languages of news sources and five languages of a parallel corpus; (b) the quality of our sentiment analysis method is largely translator independent; (c) after applying certain normalization techniques, our entity sentiment scores can be used to perform meaningful cross-cultural comparisons.
{"title":"International Sentiment Analysis for News and Blogs","authors":"Mikhail Bautin, Lohit Vijayarenu, S. Skiena","doi":"10.1609/icwsm.v2i1.18606","DOIUrl":"https://doi.org/10.1609/icwsm.v2i1.18606","url":null,"abstract":"There is a growing interest in mining opinions using sentiment analysis methods from sources such as news, blogs and product reviews. Most of these methods have been developed for English and are difficult to generalize to other languages. We explore an approach utilizing state-of-the-art machine translation technology and perform sentiment analysis on the English translation of a foreign language text. Our experiments indicate that (a) entity sentiment scores obtained by our method are statistically significantly correlated across nine languages of news sources and five languages of a parallel corpus; (b) the quality of our sentiment analysis method is largely translator independent; (c) after applying certain normalization techniques, our entity sentiment scores can be used to perform meaningful cross-cultural comparisons.","PeriodicalId":338112,"journal":{"name":"Proceedings of the International AAAI Conference on Web and Social Media","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131027550","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}
Pub Date : 2021-09-25DOI: 10.1609/icwsm.v2i1.18624
Aaditeshwar Seth, Jie Zhang
Given the rapid growth of participatory media content such as blogs, there is a need to design personalized recommender systems to recommend only useful content to users. We believe that in addition to producing useful recommendations, certain insights from media research such as simplification and opinion diversity in recommendations should form the foundations of such recommender systems, so that the behavior of the systems can be understood more closely, and modified if necessary. We propose and evaluate such a system based on a Bayesian user-model. We use the underlying social network of blog authors and readers to model the preference features for individual users. The initial results of our proposed solution are encouraging, and set the agenda for future research.
{"title":"A Social Network Based Approach to Personalized Recommendation of Participatory Media Content","authors":"Aaditeshwar Seth, Jie Zhang","doi":"10.1609/icwsm.v2i1.18624","DOIUrl":"https://doi.org/10.1609/icwsm.v2i1.18624","url":null,"abstract":"Given the rapid growth of participatory media content such as blogs, there is a need to design personalized recommender systems to recommend only useful content to users. We believe that in addition to producing useful recommendations, certain insights from media research such as simplification and opinion diversity in recommendations should form the foundations of such recommender systems, so that the behavior of the systems can be understood more closely, and modified if necessary. We propose and evaluate such a system based on a Bayesian user-model. We use the underlying social network of blog authors and readers to model the preference features for individual users. The initial results of our proposed solution are encouraging, and set the agenda for future research.","PeriodicalId":338112,"journal":{"name":"Proceedings of the International AAAI Conference on Web and Social Media","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123555861","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}
Pub Date : 2021-09-25DOI: 10.1609/icwsm.v2i1.18618
Jiang Yang, Lada A. Adamic, M. Ackerman
"Witkeys" are websites in China that form a rapidly growing web-based knowledge market. A user who posts a task also offers a small fee, and many other users submit their answers to compete. The Witkey sites fall in-between aspects of the now-defunct Google Answers (vetted experts answer questions for a fee) and Yahoo Answers (anyone can answer or ask a question). As such, these sites promise new possibilities for knowledge-sharing online communities, perhaps fostering the freelance marketplace of the future. In this paper, we investigate one of the biggest Witkey websites in China, Taskcn.com. In particular, we apply social network prestige measures to a novel construction of user and task networks based on competitive outcomes to discover the underlying properties of both users and tasks. Our results demonstrate the power of this approach: Our analysis allows us to infer relative expertise of the users and provides an understanding of the participation structure in Taskcn. The results suggest challenges and opportunities for this kind of knowledge sharing medium.
{"title":"Competing to Share Expertise: The Taskcn Knowledge Sharing Community","authors":"Jiang Yang, Lada A. Adamic, M. Ackerman","doi":"10.1609/icwsm.v2i1.18618","DOIUrl":"https://doi.org/10.1609/icwsm.v2i1.18618","url":null,"abstract":"\"Witkeys\" are websites in China that form a rapidly growing web-based knowledge market. A user who posts a task also offers a small fee, and many other users submit their answers to compete. The Witkey sites fall in-between aspects of the now-defunct Google Answers (vetted experts answer questions for a fee) and Yahoo Answers (anyone can answer or ask a question). As such, these sites promise new possibilities for knowledge-sharing online communities, perhaps fostering the freelance marketplace of the future. In this paper, we investigate one of the biggest Witkey websites in China, Taskcn.com. In particular, we apply social network prestige measures to a novel construction of user and task networks based on competitive outcomes to discover the underlying properties of both users and tasks. Our results demonstrate the power of this approach: Our analysis allows us to infer relative expertise of the users and provides an understanding of the participation structure in Taskcn. The results suggest challenges and opportunities for this kind of knowledge sharing medium.","PeriodicalId":338112,"journal":{"name":"Proceedings of the International AAAI Conference on Web and Social Media","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114154100","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}
Pub Date : 2021-09-25DOI: 10.1609/icwsm.v2i1.18631
Takashi Okamoto, K. Buza
With the popularity of social networks such as Facebook, we have greatly extended our social interactions from the physical into the digital. With social networks we have an increase in interaction opportunities; however, how we experience the interaction is rather bland. Accompanying social interactions with interesting visual feedback is one way to enrich this new space. In our demo, we present E15:FB -- a visualization application which shows a graphical representation of social interactions with individual Facebook users. The application also provides alternative methods to navigate Facebook content beyond what is provided through the Facebook website, and creates new opportunities to interact with related content outside of Facebook.
{"title":"Visualization of Social Interactions in Facebook","authors":"Takashi Okamoto, K. Buza","doi":"10.1609/icwsm.v2i1.18631","DOIUrl":"https://doi.org/10.1609/icwsm.v2i1.18631","url":null,"abstract":"With the popularity of social networks such as Facebook, we have greatly extended our social interactions from the physical into the digital. With social networks we have an increase in interaction opportunities; however, how we experience the interaction is rather bland. Accompanying social interactions with interesting visual feedback is one way to enrich this new space. In our demo, we present E15:FB -- a visualization application which shows a graphical representation of social interactions with individual Facebook users. The application also provides alternative methods to navigate Facebook content beyond what is provided through the Facebook website, and creates new opportunities to interact with related content outside of Facebook.","PeriodicalId":338112,"journal":{"name":"Proceedings of the International AAAI Conference on Web and Social Media","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114163334","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}
Pub Date : 2021-09-25DOI: 10.1609/icwsm.v2i1.18638
Jeffrey P. Bigham, Daniel S. Otero, Jessica N. DeWitt, Anna Cavender, R. Ladner
Deaf and hard of hearing students studying advanced topics in Science, Technology, Engineering, and Mathematics (STEM) lack standard terminology to enable them to learn, discuss and contribute to their chosen fields. The ASL-STEM Forum enables the diverse, thinly-spread groups that are independently creating and us1ing terminology to come together using a community-based, video-enabled web resource. A common vocabulary would provide interpreters with consistent terminology and enable deaf scientists to more easily converse from a common basis. This paper discusses the implementation of the ASL-STEM Forum, describes our approach to building a community using the site, and overviews the unique opportunities it offers for observing a language developing from the bottom-up.
{"title":"ASL-STEM Forum: A Bottom-Up Approach to Enabling American Sign Language to Grow in STEM Fields","authors":"Jeffrey P. Bigham, Daniel S. Otero, Jessica N. DeWitt, Anna Cavender, R. Ladner","doi":"10.1609/icwsm.v2i1.18638","DOIUrl":"https://doi.org/10.1609/icwsm.v2i1.18638","url":null,"abstract":"Deaf and hard of hearing students studying advanced topics in Science, Technology, Engineering, and Mathematics (STEM) lack standard terminology to enable them to learn, discuss and contribute to their chosen fields. The ASL-STEM Forum enables the diverse, thinly-spread groups that are independently creating and us1ing terminology to come together using a community-based, video-enabled web resource. A common vocabulary would provide interpreters with consistent terminology and enable deaf scientists to more easily converse from a common basis. This paper discusses the implementation of the ASL-STEM Forum, describes our approach to building a community using the site, and overviews the unique opportunities it offers for observing a language developing from the bottom-up.","PeriodicalId":338112,"journal":{"name":"Proceedings of the International AAAI Conference on Web and Social Media","volume":"410 17","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120892156","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}
Pub Date : 2021-09-25DOI: 10.1609/icwsm.v2i1.18632
Michael Toomim, Xianhang Zhang, J. Fogarty, Nathan Morris
Managing privacy of online content is difficult. We present a simple social access control where sharers specify test questions of shared knowledge, such as "what is our school mascot," instead of creating authenticated accounts and specifying explicit access control rules for all potential accessors. This demo will let attendees interact with our Facebook prototype. We will also explain prior studies that elucidate the context of photo sharing security, gauge the difficulty of creating shared knowledge questions, measure their resilience to adversarial attack, and evaluate users' abilities to understand and predict this resilience.
{"title":"Social Access Control for Social Media Using Shared Knowledge Questions","authors":"Michael Toomim, Xianhang Zhang, J. Fogarty, Nathan Morris","doi":"10.1609/icwsm.v2i1.18632","DOIUrl":"https://doi.org/10.1609/icwsm.v2i1.18632","url":null,"abstract":"Managing privacy of online content is difficult. We present a simple social access control where sharers specify test questions of shared knowledge, such as \"what is our school mascot,\" instead of creating authenticated accounts and specifying explicit access control rules for all potential accessors. This demo will let attendees interact with our Facebook prototype. We will also explain prior studies that elucidate the context of photo sharing security, gauge the difficulty of creating shared knowledge questions, measure their resilience to adversarial attack, and evaluate users' abilities to understand and predict this resilience.","PeriodicalId":338112,"journal":{"name":"Proceedings of the International AAAI Conference on Web and Social Media","volume":"2008 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127314172","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}
Pub Date : 2021-09-25DOI: 10.1609/icwsm.v2i1.18635
Navot Akiva, Eliyahu Greitzer, Yakir Krichman, Jonathan Schler
In this paper, we describe our Brand Association Map (BAM) tool which maps and visualizes the way consumers naturally think and talk about brands across billions of unaided conversations online. BAM is a semi-supervised tool that leverages text-mining algorithms to identify key correlated phrases, terms and issues out of millions of candidate terms which were derived from billions of online conversations. The most correlated phrases with a given brand are then projected and plotted onto visual bull's eye representation. BAM's visualization illustrates both the correlation level between a brand (appears in the center of the visualization) and each of the highly correlated terms as well as the inner correlations among all presented terms, where terms on the same radial angel represent a "clustered" discussion of terms frequently mentioned together. We found BAM useful for extracting various intuitions and beliefs that are highly correlated with brands to better grasp how consumers really contextualize them, out of massive consumer generated media (CGM) documents.
{"title":"Mining and Visualizing Online Web Content Using BAM: Brand Association Map","authors":"Navot Akiva, Eliyahu Greitzer, Yakir Krichman, Jonathan Schler","doi":"10.1609/icwsm.v2i1.18635","DOIUrl":"https://doi.org/10.1609/icwsm.v2i1.18635","url":null,"abstract":"In this paper, we describe our Brand Association Map (BAM) tool which maps and visualizes the way consumers naturally think and talk about brands across billions of unaided conversations online. BAM is a semi-supervised tool that leverages text-mining algorithms to identify key correlated phrases, terms and issues out of millions of candidate terms which were derived from billions of online conversations. The most correlated phrases with a given brand are then projected and plotted onto visual bull's eye representation. BAM's visualization illustrates both the correlation level between a brand (appears in the center of the visualization) and each of the highly correlated terms as well as the inner correlations among all presented terms, where terms on the same radial angel represent a \"clustered\" discussion of terms frequently mentioned together. We found BAM useful for extracting various intuitions and beliefs that are highly correlated with brands to better grasp how consumers really contextualize them, out of massive consumer generated media (CGM) documents.","PeriodicalId":338112,"journal":{"name":"Proceedings of the International AAAI Conference on Web and Social Media","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127997629","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}
Pub Date : 2021-09-25DOI: 10.1609/icwsm.v2i1.18628
G. Walejko, Thomas Ksiazek
Digital media lowers barriers to entry and has the ability to renegotiate traditional news-making power structures. However, it remains to be seen whether or not the people that use tools like blogs actually challenge those frameworks. Offline reporters predominantly use government officials as sources while online journalists and newspaper institutions typically cite their own pages and posts. In order to understand whether or not journalistic norms are challenged in the blogosphere, we look at the sourcing practices of a diverse group of 40 bloggers. Specifically, we sample 400 blogposts that discussed global warming between 2004 and May of 2007. Operationalizing hyperlinks as sources, we then code the 3264 hyperlinks in these posts. Results indicate that government sources are linked to the least. Instead, bloggers tend to link to the online versions of traditional news media as well as to other blogs. However, we find that bloggers also link to miscellaneous and civic sources such as academics and non-profit organizations about one-quarter of the time, somewhat challenging the dominance of government and traditional media. We conclude that blogging on non-traditional topics may subvert who gets heard in an online world, but further research is needed on this topic.
{"title":"The Politics of Sourcing: A Study of Journalistic Practices in the Blogosphere","authors":"G. Walejko, Thomas Ksiazek","doi":"10.1609/icwsm.v2i1.18628","DOIUrl":"https://doi.org/10.1609/icwsm.v2i1.18628","url":null,"abstract":"Digital media lowers barriers to entry and has the ability to renegotiate traditional news-making power structures. However, it remains to be seen whether or not the people that use tools like blogs actually challenge those frameworks. Offline reporters predominantly use government officials as sources while online journalists and newspaper institutions typically cite their own pages and posts. In order to understand whether or not journalistic norms are challenged in the blogosphere, we look at the sourcing practices of a diverse group of 40 bloggers. Specifically, we sample 400 blogposts that discussed global warming between 2004 and May of 2007. Operationalizing hyperlinks as sources, we then code the 3264 hyperlinks in these posts. Results indicate that government sources are linked to the least. Instead, bloggers tend to link to the online versions of traditional news media as well as to other blogs. However, we find that bloggers also link to miscellaneous and civic sources such as academics and non-profit organizations about one-quarter of the time, somewhat challenging the dominance of government and traditional media. We conclude that blogging on non-traditional topics may subvert who gets heard in an online world, but further research is needed on this topic.","PeriodicalId":338112,"journal":{"name":"Proceedings of the International AAAI Conference on Web and Social Media","volume":"132 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128302445","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}
Pub Date : 2021-09-25DOI: 10.1609/icwsm.v2i1.18651
Sang Su Lee, Dongwoo Won, D. McLeod
This paper presents an analysis of the correlation of annotated information unit (textual) tags and geographical identification metadata geotags. In this paper, to make it possible for geotagging to be used in analysis with tagging, we prove that there is a strong correlation between tagging and geotagging information. Our approach uses tag similarity and newly employed geographical distribution similarity to determine inter-relationships among tags and geotags. From our initial experiments, we show that the power law is established between tag similarity and geographical distribution similarity; they are strongly correlated and the correlation can be used to find more relevant tags in the tag space. The power law, which is any polynomial relationship that exhibits the property of scale invariance, confirms that there is the relationship between tagging and geotagging and the relationship is scalable in size of tags and geotags.
{"title":"Discovering Relationships among Tags and Geotags","authors":"Sang Su Lee, Dongwoo Won, D. McLeod","doi":"10.1609/icwsm.v2i1.18651","DOIUrl":"https://doi.org/10.1609/icwsm.v2i1.18651","url":null,"abstract":"This paper presents an analysis of the correlation of annotated information unit (textual) tags and geographical identification metadata geotags. In this paper, to make it possible for geotagging to be used in analysis with tagging, we prove that there is a strong correlation between tagging and geotagging information. Our approach uses tag similarity and newly employed geographical distribution similarity to determine inter-relationships among tags and geotags. From our initial experiments, we show that the power law is established between tag similarity and geographical distribution similarity; they are strongly correlated and the correlation can be used to find more relevant tags in the tag space. The power law, which is any polynomial relationship that exhibits the property of scale invariance, confirms that there is the relationship between tagging and geotagging and the relationship is scalable in size of tags and geotags.","PeriodicalId":338112,"journal":{"name":"Proceedings of the International AAAI Conference on Web and Social Media","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129772455","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：