Social tagging systems have established themselves as an important part in
day's web and have attracted the interest from our research community in a
riety of investigations. The overall vision of our community is that simply
rough interactions with the system, i.e., through tagging and sharing of
sources, users would contribute to building useful semantic structures as
ll as resource indexes using uncontrolled vocabulary not only due to the
sy-to-use mechanics. Henceforth, a variety of assumptions about social
gging systems have emerged, yet testing them has been difficult due to the
sence of suitable data. In this work we thoroughly investigate three
ailable assumptions - e.g., is a tagging system really social? - by examining
ve log data gathered from the real-world public social tagging system
bSonomy. Our empirical results indicate that while some of these assumptions
ld to a certain extent, other assumptions need to be reflected and viewed in
very critical light. Our observations have implications for the design of
ture search and other algorithms to better reflect the actual user behavior.

@techreport{doerfel2014course, author = {Doerfel, Stephan and Zoller, Daniel and Singer, Philipp and Niebler, Thomas and Hotho, Andreas and Strohmaier, Markus}, title = {Of course we share! Testing Assumptions about Social Tagging Systems}, year = {2014}, note = {cite arxiv:1401.0629}, url = {http://arxiv.org/abs/1401.0629}, keywords = {2014, analysis, assumptions, bibsonomy, data, folksonomy, log, myown, share, social, tagging, testing, weblog}, abstract = {Social tagging systems have established themselves as an important part in
day's web and have attracted the interest from our research community in a
riety of investigations. The overall vision of our community is that simply
rough interactions with the system, i.e., through tagging and sharing of
sources, users would contribute to building useful semantic structures as
ll as resource indexes using uncontrolled vocabulary not only due to the
sy-to-use mechanics. Henceforth, a variety of assumptions about social
gging systems have emerged, yet testing them has been difficult due to the
sence of suitable data. In this work we thoroughly investigate three
ailable assumptions - e.g., is a tagging system really social? - by examining
ve log data gathered from the real-world public social tagging system
bSonomy. Our empirical results indicate that while some of these assumptions
ld to a certain extent, other assumptions need to be reflected and viewed in
very critical light. Our observations have implications for the design of
ture search and other algorithms to better reflect the actual user behavior.} }

%0 = techreport %A = Doerfel, Stephan and Zoller, Daniel and Singer, Philipp and Niebler, Thomas and Hotho, Andreas and Strohmaier, Markus %D = 2014 %T = Of course we share! Testing Assumptions about Social Tagging Systems %U = http://arxiv.org/abs/1401.0629

The ever-growing flood of new scientific articles requires novel retrieval mechanisms. One means for mitigating this instance of the information overload phenomenon are collaborative tagging systems, that allow users to select, share and annotate references to publications. These systems employ recommendation algorithms to present to their users personalized lists of interesting and relevant publications. In this paper we analyze different ways to incorporate social data and metadata from collaborative tagging systems into the graph-based ranking algorithm FolkRank to utilize it for recommending scientific articles to users of the social bookmarking system BibSonomy. We compare the results to those of Collaborative Filtering, which has previously been applied for resource recommendation.

@inproceedings{doerfel2012leveraging, author = {Doerfel, Stephan and Jäschke, Robert and Hotho, Andreas and Stumme, Gerd}, title = {Leveraging Publication Metadata and Social Data into FolkRank for Scientific Publication Recommendation}, booktitle = {Proceedings of the 4th ACM RecSys workshop on Recommender systems and the social web}, series = {RSWeb '12}, publisher = {ACM}, address = {New York, NY, USA}, year = {2012}, pages = {9--16}, url = {http://doi.acm.org/10.1145/2365934.2365937}, doi = {10.1145/2365934.2365937}, isbn = {978-1-4503-1638-5}, keywords = {2012, data, info20pub, itegpub, itemRecommendation, leveraging, metadata, myown, publication, reco, recsys, social}, abstract = {The ever-growing flood of new scientific articles requires novel retrieval mechanisms. One means for mitigating this instance of the information overload phenomenon are collaborative tagging systems, that allow users to select, share and annotate references to publications. These systems employ recommendation algorithms to present to their users personalized lists of interesting and relevant publications. In this paper we analyze different ways to incorporate social data and metadata from collaborative tagging systems into the graph-based ranking algorithm FolkRank to utilize it for recommending scientific articles to users of the social bookmarking system BibSonomy. We compare the results to those of Collaborative Filtering, which has previously been applied for resource recommendation.} }

%0 = inproceedings %A = Doerfel, Stephan and Jäschke, Robert and Hotho, Andreas and Stumme, Gerd %B = Proceedings of the 4th ACM RecSys workshop on Recommender systems and the social web %C = New York, NY, USA %D = 2012 %I = ACM %T = Leveraging Publication Metadata and Social Data into FolkRank for Scientific Publication Recommendation %U = http://doi.acm.org/10.1145/2365934.2365937

Teaching machines to understand human communication is one of the central goals of artificial intelligence. Psychological research indicates that human associations are an essential requirement to understand human communication. In this paper the hypothesis is presented, that simulating human associations with the help of Linked Data could greatly improve text understanding capabilities of machines. To more thoroughly investigate whether human associations can be simulated with Linked Data, two preliminary problems are identified: (i) There does not seem to be a reasonable ground truth for human associations and (ii) while human associations have different strengths, Linked Data treats all triples equally and does not provide edge weights. Two ideas for games in accordance with Luis von Ahn's Games with a Purpose are proposed, turning the tedious process of entering associations or ratings into fun games.

@inproceedings{hees2010linked, author = {Hees, Jörn and Roth-Berghofer, Thomas and Dengel, Andreas}, title = {Linked Data Games: Simulating Human Association with Linked Data}, editor = {Atzmüller, Martin and Benz, Dominik and Hotho, Andreas and Stumme, Gerd}, booktitle = {Proceedings of LWA2010 - Workshop-Woche: Lernen, Wissen & Adaptivitaet}, address = {Kassel, Germany}, year = {2010}, keywords = {data, games, linked, simulating}, abstract = {Teaching machines to understand human communication is one of the central goals of artificial intelligence. Psychological research indicates that human associations are an essential requirement to understand human communication. In this paper the hypothesis is presented, that simulating human associations with the help of Linked Data could greatly improve text understanding capabilities of machines. To more thoroughly investigate whether human associations can be simulated with Linked Data, two preliminary problems are identified: (i) There does not seem to be a reasonable ground truth for human associations and (ii) while human associations have different strengths, Linked Data treats all triples equally and does not provide edge weights. Two ideas for games in accordance with Luis von Ahn's Games with a Purpose are proposed, turning the tedious process of entering associations or ratings into fun games.} }

%0 = inproceedings %A = Hees, Jörn and Roth-Berghofer, Thomas and Dengel, Andreas %B = Proceedings of LWA2010 - Workshop-Woche: Lernen, Wissen & Adaptivitaet %C = Kassel, Germany %D = 2010 %T = Linked Data Games: Simulating Human Association with Linked Data

Understanding how users behave when they connect to social networking sites creates opportunities for better interface design, richer studies of social interactions, and improved design of content distribution systems. In this paper, we present a first of a kind analysis of user workloads in online social networks. Our study is based on detailed clickstream data, collected over a 12-day period, summarizing HTTP sessions of 37,024 users who accessed four popular social networks: Orkut, MySpace, Hi5, and LinkedIn. The data were collected from a social network aggregator website in Brazil, which enables users to connect to multiple social networks with a single authentication. Our analysis of the clickstream data reveals key features of the social network workloads, such as how frequently people connect to social networks and for how long, as well as the types and sequences of activities that users conduct on these sites. Additionally, we crawled the social network topology of Orkut, so that we could analyze user interaction data in light of the social graph. Our data analysis suggests insights into how users interact with friends in Orkut, such as how frequently users visit their friends' or non-immediate friends' pages. In summary, our analysis demonstrates the power of using clickstream data in identifying patterns in social network workloads and social interactions. Our analysis shows that browsing, which cannot be inferred from crawling publicly available data, accounts for 92% of all user activities. Consequently, compared to using only crawled data, considering silent interactions like browsing friends' pages increases the measured level of interaction among users.

@inproceedings{benevenuto2009characterizing, author = {Benevenuto, Fabrcio and Rodrigues, Tiago and Cha, Meeyoung and Almeida, Virglio}, title = {Characterizing User Behavior in Online Social Networks}, booktitle = {Proceedings of the 9th ACM SIGCOMM Conference on Internet Measurement Conference}, series = {IMC '09}, publisher = {ACM}, address = {New York, NY, USA}, year = {2009}, pages = {49--62}, url = {http://doi.acm.org/10.1145/1644893.1644900}, doi = {10.1145/1644893.1644900}, isbn = {978-1-60558-771-4}, keywords = {analysis, behavior, clickstream, data, log, network, sna, social, user}, abstract = {Understanding how users behave when they connect to social networking sites creates opportunities for better interface design, richer studies of social interactions, and improved design of content distribution systems. In this paper, we present a first of a kind analysis of user workloads in online social networks. Our study is based on detailed clickstream data, collected over a 12-day period, summarizing HTTP sessions of 37,024 users who accessed four popular social networks: Orkut, MySpace, Hi5, and LinkedIn. The data were collected from a social network aggregator website in Brazil, which enables users to connect to multiple social networks with a single authentication. Our analysis of the clickstream data reveals key features of the social network workloads, such as how frequently people connect to social networks and for how long, as well as the types and sequences of activities that users conduct on these sites. Additionally, we crawled the social network topology of Orkut, so that we could analyze user interaction data in light of the social graph. Our data analysis suggests insights into how users interact with friends in Orkut, such as how frequently users visit their friends' or non-immediate friends' pages. In summary, our analysis demonstrates the power of using clickstream data in identifying patterns in social network workloads and social interactions. Our analysis shows that browsing, which cannot be inferred from crawling publicly available data, accounts for 92% of all user activities. Consequently, compared to using only crawled data, considering silent interactions like browsing friends' pages increases the measured level of interaction among users.} }

%0 = inproceedings %A = Benevenuto, Fabrcio and Rodrigues, Tiago and Cha, Meeyoung and Almeida, Virglio %B = Proceedings of the 9th ACM SIGCOMM Conference on Internet Measurement Conference %C = New York, NY, USA %D = 2009 %I = ACM %T = Characterizing User Behavior in Online Social Networks %U = http://doi.acm.org/10.1145/1644893.1644900

@article{Go_Huang_Bhayani_2009, author = {Go, A and Huang, L and Bhayani, R}, title = {Sentiment Analysis of Twitter Data}, journal = {Entropy}, publisher = {Association for Computational Linguistics}, year = {2009}, volume = {2009}, number = {June}, pages = {17}, url = {http://nlp.stanford.edu/courses/cs224n/2009/fp/3.pdf}, keywords = {analysis, data, evaluation, sentiment, twitter} }

%0 = article %A = Go, A and Huang, L and Bhayani, R %D = 2009 %I = Association for Computational Linguistics %T = Sentiment Analysis of Twitter Data %U = http://nlp.stanford.edu/courses/cs224n/2009/fp/3.pdf

@inproceedings{conf/sigmod/WangWYY02, author = {Wang, Haixun and 0010, Wei Wang and Yang, Jiong and Yu, Philip S.}, title = {Clustering by pattern similarity in large data sets.}, editor = {Franklin, Michael J. and Moon, Bongki and Ailamaki, Anastassia}, booktitle = {SIGMOD Conference}, publisher = {ACM}, year = {2002}, pages = {394-405}, url = {http://dblp.uni-trier.de/db/conf/sigmod/sigmod2002.html#WangWYY02}, isbn = {1-58113-497-5}, keywords = {algorithm, clustering, data, fca?, large, pClusters, paper, pattern} }

%0 = inproceedings %A = Wang, Haixun and 0010, Wei Wang and Yang, Jiong and Yu, Philip S. %B = SIGMOD Conference %D = 2002 %I = ACM %T = Clustering by pattern similarity in large data sets. %U = http://dblp.uni-trier.de/db/conf/sigmod/sigmod2002.html#WangWYY02