@inproceedings{atzmueller2011facetoface, author = {Atzmueller, Martin and Doerfel, Stephan and Hotho, Andreas and Mitzlaff, Folke and Stumme, Gerd}, title = {Face-to-Face Contacts during a Conference: Communities, Roles, and Key Players}, booktitle = {Proc. Workshop on Mining Ubiquitous and Social Environments (MUSE 2011) at ECML/PKDD 2011}, year = {2011}, keywords = {2011, analysis, communities, community, discovery, face, itegpub, knowledge, mining, myown, rfid, venus, venuspub} }

%0 = inproceedings %A = Atzmueller, Martin and Doerfel, Stephan and Hotho, Andreas and Mitzlaff, Folke and Stumme, Gerd %B = Proc. Workshop on Mining Ubiquitous and Social Environments (MUSE 2011) at ECML/PKDD 2011 %D = 2011 %T = Face-to-Face Contacts during a Conference: Communities, Roles, and Key Players

@article{an2004characterizing, author = {An, Yuan and Janssen, Jeannette and Milios, Evangelos E.}, title = {Characterizing and Mining the Citation Graph of the Computer Science Literature}, journal = {Knowl. Inf. Syst.}, publisher = {Springer-Verlag New York, Inc.}, address = {New York, NY, USA}, year = {2004}, volume = {6}, pages = {664--678}, url = {http://dx.doi.org/10.1007/s10115-003-0128-3}, doi = {http://dx.doi.org/10.1007/s10115-003-0128-3}, issn = {0219-1377}, keywords = {10th, Citation, characterizing, citation, computer, graph, mining} }

%0 = article %A = An, Yuan and Janssen, Jeannette and Milios, Evangelos E. %C = New York, NY, USA %D = 2004 %I = Springer-Verlag New York, Inc. %T = Characterizing and Mining the Citation Graph of the Computer Science Literature %U = http://dx.doi.org/10.1007/s10115-003-0128-3

@inproceedings{default, author = {Pak, Alexander and Paroubek, Patrick}, title = {Twitter as a Corpus for Sentiment Analysis and Opinion Mining}, year = {2010}, volume = {2010}, pages = {1320-1326}, url = {http://www.mendeley.com/research/twitter-corpus-sentiment-analysis-opinion-mining-18/}, keywords = {emotion, mining, seminar, sentiment, twitter} }

%0 = inproceedings %A = Pak, Alexander and Paroubek, Patrick %D = 2010 %T = Twitter as a Corpus for Sentiment Analysis and Opinion Mining %U = http://www.mendeley.com/research/twitter-corpus-sentiment-analysis-opinion-mining-18/

@incollection{atzmueller2012facetoface, author = {Atzmueller, Martin and Doerfel, Stephan and Hotho, Andreas and Mitzlaff, Folke and Stumme, Gerd}, title = {Face-to-Face Contacts at a Conference: Dynamics of Communities and Roles}, booktitle = {Modeling and Mining Ubiquitous Social Media}, series = {LNAI}, publisher = {Springer Verlag}, address = {Heidelberg, Germany}, year = {2012}, volume = {7472}, keywords = {2012, conference, contacts, dynamics, face, intelligence, itegpub, kde, mining, myown, social, ubiquitous, venus, venuspub} }

%0 = incollection %A = Atzmueller, Martin and Doerfel, Stephan and Hotho, Andreas and Mitzlaff, Folke and Stumme, Gerd %B = Modeling and Mining Ubiquitous Social Media %C = Heidelberg, Germany %D = 2012 %I = Springer Verlag %T = Face-to-Face Contacts at a Conference: Dynamics of Communities and Roles

@inproceedings{jones1998usage, author = {Jones, Steve and Cunningham, Sally Jo and McNab, Rodger}, title = {Usage analysis of a digital library}, booktitle = {Proceedings of the third ACM conference on Digital libraries}, series = {DL '98}, publisher = {ACM}, address = {New York, NY, USA}, year = {1998}, pages = {293--294}, url = {http://doi.acm.org/10.1145/276675.276739}, doi = {10.1145/276675.276739}, isbn = {0-89791-965-3}, keywords = {analysis, digital, library, logs, mining, usage, weblog} }

%0 = inproceedings %A = Jones, Steve and Cunningham, Sally Jo and McNab, Rodger %B = Proceedings of the third ACM conference on Digital libraries %C = New York, NY, USA %D = 1998 %I = ACM %T = Usage analysis of a digital library %U = http://doi.acm.org/10.1145/276675.276739

@article{nicholas2005scholarly, author = {Nicholas, David and Huntington, Paul and Watkinson, Anthony}, title = {Scholarly journal usage: the results of deep log analysis}, journal = {Journal of Documentation}, publisher = {Emerald Group Publishing Limited}, address = {Bingley}, year = {2005}, volume = {61}, number = {2}, pages = {248--280}, url = {http://www.emeraldinsight.com/journals.htm?articleid=1465024&show=abstract}, keywords = {Scholarly, analysis, deep, journal, log, mining, usage, weblog} }

%0 = article %A = Nicholas, David and Huntington, Paul and Watkinson, Anthony %C = Bingley %D = 2005 %I = Emerald Group Publishing Limited %T = Scholarly journal usage: the results of deep log analysis %U = http://www.emeraldinsight.com/journals.htm?articleid=1465024&show=abstract

In this paper we present an analysis of an AltaVista Search Engine query log consisting of approximately 1 billion entries for search requests over a period of six weeks. This represents almost 285 million user sessions, each an attempt to fill a single information need. We present an analysis of individual queries, query duplication, and query sessions. We also present results of a correlation analysis of the log entries, studying the interaction of terms within queries. Our data supports the conjecture that web users differ significantly from the user assumed in the standard information retrieval literature. Specifically, we show that web users type in short queries, mostly look at the first 10 results only, and seldom modify the query. This suggests that traditional information retrieval techniques may not work well for answering web search requests. The correlation analysis showed that the most highly correlated items are constituents of phrases. This result indicates it may be useful for search engines to consider search terms as parts of phrases even if the user did not explicitly specify them as such.

@article{silverstein1999analysis, author = {Silverstein, Craig and Marais, Hannes and Henzinger, Monika and Moricz, Michael}, title = {Analysis of a very large web search engine query log}, journal = {SIGIR Forum}, publisher = {ACM}, address = {New York, NY, USA}, year = {1999}, volume = {33}, number = {1}, pages = {6--12}, url = {http://doi.acm.org/10.1145/331403.331405}, doi = {10.1145/331403.331405}, issn = {0163-5840}, keywords = {altavista, behaviour, engine, log, mining, query, search, weblog}, abstract = {In this paper we present an analysis of an AltaVista Search Engine query log consisting of approximately 1 billion entries for search requests over a period of six weeks. This represents almost 285 million user sessions, each an attempt to fill a single information need. We present an analysis of individual queries, query duplication, and query sessions. We also present results of a correlation analysis of the log entries, studying the interaction of terms within queries. Our data supports the conjecture that web users differ significantly from the user assumed in the standard information retrieval literature. Specifically, we show that web users type in short queries, mostly look at the first 10 results only, and seldom modify the query. This suggests that traditional information retrieval techniques may not work well for answering web search requests. The correlation analysis showed that the most highly correlated items are constituents of phrases. This result indicates it may be useful for search engines to consider search terms as parts of phrases even if the user did not explicitly specify them as such.} }

%0 = article %A = Silverstein, Craig and Marais, Hannes and Henzinger, Monika and Moricz, Michael %C = New York, NY, USA %D = 1999 %I = ACM %T = Analysis of a very large web search engine query log %U = http://doi.acm.org/10.1145/331403.331405

The use of data stored in transaction logs of Web search engines, Intranets, and Web sites can provide valuable insight into understanding the information-searching process of online searchers. This understanding can enlighten information system design, interface development, and devising the information architecture for content collections. This article presents a review and foundation for conducting Web search transaction log analysis. A methodology is outlined consisting of three stages, which are collection, preparation, and analysis. The three stages of the methodology are presented in detail with discussions of goals, metrics, and processes at each stage. Critical terms in transaction log analysis for Web searching are defined. The strengths and limitations of transaction log analysis as a research method are presented. An application to log client-side interactions that supplements transaction logs is reported on, and the application is made available for use by the research community. Suggestions are provided on ways to leverage the strengths of, while addressing the limitations of, transaction log analysis for Web-searching research. Finally, a complete flat text transaction log from a commercial search engine is available as supplementary material with this manuscript.

@article{jansen2006search, author = {Jansen, Bernard J.}, title = {Search log analysis: What it is, what's been done, how to do it}, journal = {Library & Information Science Research}, year = {2006}, volume = {28}, number = {3}, pages = {407 - 432}, url = {http://www.sciencedirect.com/science/article/pii/S0740818806000673}, doi = {10.1016/j.lisr.2006.06.005}, issn = {0740-8188}, keywords = {analysis, howto, log, mining, search, weblog}, abstract = {The use of data stored in transaction logs of Web search engines, Intranets, and Web sites can provide valuable insight into understanding the information-searching process of online searchers. This understanding can enlighten information system design, interface development, and devising the information architecture for content collections. This article presents a review and foundation for conducting Web search transaction log analysis. A methodology is outlined consisting of three stages, which are collection, preparation, and analysis. The three stages of the methodology are presented in detail with discussions of goals, metrics, and processes at each stage. Critical terms in transaction log analysis for Web searching are defined. The strengths and limitations of transaction log analysis as a research method are presented. An application to log client-side interactions that supplements transaction logs is reported on, and the application is made available for use by the research community. Suggestions are provided on ways to leverage the strengths of, while addressing the limitations of, transaction log analysis for Web-searching research. Finally, a complete flat text transaction log from a commercial search engine is available as supplementary material with this manuscript.} }

%0 = article %A = Jansen, Bernard J. %D = 2006 %T = Search log analysis: What it is, what's been done, how to do it %U = http://www.sciencedirect.com/science/article/pii/S0740818806000673

We describe the web usage mining activities of an on-going project, called ClickWorld, that aims at extracting models of the navigational behaviour of a web site users. The models are inferred from the access logs of a web server by means of data and web mining techniques. The extracted knowledge is deployed to the purpose of offering a personalized and proactive view of the web services to users. We first describe the preprocessing steps on access logs necessary to clean, select and prepare data for knowledge extraction. Then we show two sets of experiments: the first one tries to predict the sex of a user based on the visited web pages, and the second one tries to predict whether a user might be interested in visiting a section of the site.

@incollection{baglioni2003preprocessing, author = {Baglioni, M. and Ferrara, U. and Romei, A. and Ruggieri, S. and Turini, F.}, title = {Preprocessing and Mining Web Log Data for Web Personalization}, editor = {Cappelli, Amedeo and Turini, Franco}, booktitle = {AI*IA 2003: Advances in Artificial Intelligence}, series = {Lecture Notes in Computer Science}, publisher = {Springer Berlin Heidelberg}, year = {2003}, volume = {2829}, pages = {237-249}, url = {http://dx.doi.org/10.1007/978-3-540-39853-0_20}, doi = {10.1007/978-3-540-39853-0_20}, isbn = {978-3-540-20119-9}, keywords = {classification, gender, interest, mining, user, weblog}, abstract = {We describe the web usage mining activities of an on-going project, called ClickWorld, that aims at extracting models of the navigational behaviour of a web site users. The models are inferred from the access logs of a web server by means of data and web mining techniques. The extracted knowledge is deployed to the purpose of offering a personalized and proactive view of the web services to users. We first describe the preprocessing steps on access logs necessary to clean, select and prepare data for knowledge extraction. Then we show two sets of experiments: the first one tries to predict the sex of a user based on the visited web pages, and the second one tries to predict whether a user might be interested in visiting a section of the site.} }

%0 = incollection %A = Baglioni, M. and Ferrara, U. and Romei, A. and Ruggieri, S. and Turini, F. %B = AI*IA 2003: Advances in Artificial Intelligence %D = 2003 %I = Springer Berlin Heidelberg %T = Preprocessing and Mining Web Log Data for Web Personalization %U = http://dx.doi.org/10.1007/978-3-540-39853-0_20

Previous work on understanding user web search behavior has focused on how people search and what they are searching for, but not why they are searching. In this paper, we describe a framework for understanding the underlying goals of user searches, and our experience in using the framework to manually classify queries from a web search engine. Our analysis suggests that so-called navigational" searches are less prevalent than generally believed while a previously unexplored "resource-seeking" goal may account for a large fraction of web searches. We also illustrate how this knowledge of user search goals might be used to improve future web search engines.

@inproceedings{rose2004understanding, author = {Rose, Daniel E. and Levinson, Danny}, title = {Understanding user goals in web search}, booktitle = {Proceedings of the 13th international conference on World Wide Web}, series = {WWW '04}, publisher = {ACM}, address = {New York, NY, USA}, year = {2004}, pages = {13--19}, url = {http://doi.acm.org/10.1145/988672.988675}, doi = {10.1145/988672.988675}, isbn = {1-58113-844-X}, keywords = {goal, intention, mining, search, user, weblog}, abstract = {Previous work on understanding user web search behavior has focused on how people search and what they are searching for, but not why they are searching. In this paper, we describe a framework for understanding the underlying goals of user searches, and our experience in using the framework to manually classify queries from a web search engine. Our analysis suggests that so-called navigational" searches are less prevalent than generally believed while a previously unexplored "resource-seeking" goal may account for a large fraction of web searches. We also illustrate how this knowledge of user search goals might be used to improve future web search engines.} }

%0 = inproceedings %A = Rose, Daniel E. and Levinson, Danny %B = Proceedings of the 13th international conference on World Wide Web %C = New York, NY, USA %D = 2004 %I = ACM %T = Understanding user goals in web search %U = http://doi.acm.org/10.1145/988672.988675

Abstract: Frequent pattern mining is a heavily researched area in the field of data mining with wide range of applications. One of them is to use frequent pattern discovery methods in Web log data. Discovering hidden information from Web log data is called Web usage mining. The aim of discovering frequent patterns in Web log data is to obtain information about the navigational behavior of the users. This can be used for advertising purposes, for creating dynamic user profiles etc. In this paper three pattern mining approaches are investigated from the Web usage mining point of view. The different patterns in Web log mining are page sets, page sequences and page graphs.

@article{ivncsy2006frequent, author = {Iváncsy, Renáta and Vajk, István}, title = {Frequent Pattern Mining in Web Log Data}, journal = {Acta Polytechnica Hungarica}, year = {2006}, volume = {3}, number = {1}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.101.4559}, keywords = {association, frequent, itemset, mining, pattern, rule, weblog}, abstract = {Abstract: Frequent pattern mining is a heavily researched area in the field of data mining with wide range of applications. One of them is to use frequent pattern discovery methods in Web log data. Discovering hidden information from Web log data is called Web usage mining. The aim of discovering frequent patterns in Web log data is to obtain information about the navigational behavior of the users. This can be used for advertising purposes, for creating dynamic user profiles etc. In this paper three pattern mining approaches are investigated from the Web usage mining point of view. The different patterns in Web log mining are page sets, page sequences and page graphs.} }

%0 = article %A = Iváncsy, Renáta and Vajk, István %D = 2006 %T = Frequent Pattern Mining in Web Log Data %U = http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.101.4559

@article{suneetha2005identifying, author = {Suneetha, K. R. and Krishnamoorthy, K. R.}, title = {Identifying User Behavior by Analyzing Web Server
cess Log File}, journal = {International Journal of Computer Science and Network Security}, year = {2005}, volume = {9}, number = {4}, pages = {327-332}, keywords = {asociation, count, hit, mining, rules, weblog} }

%0 = article %A = Suneetha, K. R. and Krishnamoorthy, K. R. %D = 2005 %T = Identifying User Behavior by Analyzing Web Server
cess Log File

The logs of four universities using the OhioLINK journal system were evaluated for a period of fifteen months using deep log analysis methods in order to compare and contrast the information seeking behaviour of their users. Large differences were found, especially between the research and teaching universities. Methodological problems associated with making the comparisons are discussed in some detail especially in terms of defining online sessions.

@article{nicholas2007diversity, author = {Nicholas, David and Huntington, Paul and Jamali, Hamid R.}, title = {Diversity in the Information Seeking Behaviour of the Virtual Scholar: Institutional Comparisons}, journal = {The Journal of Academic Librarianship}, year = {2007}, volume = {33}, number = {6}, pages = {629 - 638}, url = {http://www.sciencedirect.com/science/article/pii/S0099133307001759}, doi = {10.1016/j.acalib.2007.09.001}, issn = {0099-1333}, keywords = {Diversity, behaviour, mining, oscholar, seeking, weblog}, abstract = {The logs of four universities using the OhioLINK journal system were evaluated for a period of fifteen months using deep log analysis methods in order to compare and contrast the information seeking behaviour of their users. Large differences were found, especially between the research and teaching universities. Methodological problems associated with making the comparisons are discussed in some detail especially in terms of defining online sessions.} }

%0 = article %A = Nicholas, David and Huntington, Paul and Jamali, Hamid R. %D = 2007 %T = Diversity in the Information Seeking Behaviour of the Virtual Scholar: Institutional Comparisons %U = http://www.sciencedirect.com/science/article/pii/S0099133307001759

Metrics derived from user visits or sessions provide a means of evaluating Websites and an important insight into online information seeking behaviour, the most important of them being the duration of sessions and the number of pages viewed in a session, a possible busyness indicator. However, the identification of session (termed often ‘sessionization’) is fraught with difficulty in that there is no way of determining from a transactional log file that a user has ended their session. No one logs out. Instead a session delimiter has to be applied and this is typically done on the basis of a standard period of inactivity. To date researchers have discussed the issue of a time out delimiter in terms of a single value and if a page view time exceeds the cut-off value the session is deemed to have ended. This approach assumes that page view time is a single distribution and that the cut-off value is one point on that distribution. The authors however argue that page time distribution is composed of a number of quite separate view time distributions because of the marked differences in view times between pages (abstract, contents page, full text). This implies that a number of timeout delimiters should be applied. Employing data from a study of the OhioLINK digital journal library, the authors demonstrate how the setting of a time out delimiter impacts on the estimate of page view time and the number of estimated session. Furthermore, they also show how a number of timeout delimiters might apply and they argue that this gives a better and more robust estimate of the number of sessions, session time and page view time compared to an application of a single timeout delimiter.

@article{huntington2008website, author = {Huntington, Paul and Nicholas, David and Jamali, Hamid R.}, title = {Website usage metrics: A re-assessment of session data}, journal = {Information Processing & Management}, year = {2008}, volume = {44}, number = {1}, pages = {358 - 372}, note = {Evaluation of Interactive Information Retrieval Systems}, url = {http://www.sciencedirect.com/science/article/pii/S0306457307000817}, doi = {10.1016/j.ipm.2007.03.003}, issn = {0306-4573}, keywords = {mining, proxy, session, timeout, weblog}, abstract = {Metrics derived from user visits or sessions provide a means of evaluating Websites and an important insight into online information seeking behaviour, the most important of them being the duration of sessions and the number of pages viewed in a session, a possible busyness indicator. However, the identification of session (termed often ‘sessionization’) is fraught with difficulty in that there is no way of determining from a transactional log file that a user has ended their session. No one logs out. Instead a session delimiter has to be applied and this is typically done on the basis of a standard period of inactivity. To date researchers have discussed the issue of a time out delimiter in terms of a single value and if a page view time exceeds the cut-off value the session is deemed to have ended. This approach assumes that page view time is a single distribution and that the cut-off value is one point on that distribution. The authors however argue that page time distribution is composed of a number of quite separate view time distributions because of the marked differences in view times between pages (abstract, contents page, full text). This implies that a number of timeout delimiters should be applied. Employing data from a study of the OhioLINK digital journal library, the authors demonstrate how the setting of a time out delimiter impacts on the estimate of page view time and the number of estimated session. Furthermore, they also show how a number of timeout delimiters might apply and they argue that this gives a better and more robust estimate of the number of sessions, session time and page view time compared to an application of a single timeout delimiter.} }

%0 = article %A = Huntington, Paul and Nicholas, David and Jamali, Hamid R. %D = 2008 %T = Website usage metrics: A re-assessment of session data %U = http://www.sciencedirect.com/science/article/pii/S0306457307000817

Transaction logs of NAVER, a major Korean Web search engine, were analyzed to track the information-seeking behavior of Korean Web users. These transaction logs include more than 40 million queries collected over 1 week. This study examines current transaction log analysis methodologies and proposes a method for log cleaning, session definition, and query classification. A term definition method which is necessary for Korean transaction log analysis is also discussed. The results of this study show that users behave in a simple way: they type in short queries with a few query terms, seldom use advanced features, and view few results' pages. Users also behave in a passive way: they seldom change search environments set by the system. It is of interest that users tend to change their queries totally rather than adding or deleting terms to modify the previous queries. The results of this study might contribute to the development of more efficient and effective Web search engines and services.

@article{park2005searching, author = {Park, Soyeon and Lee, Joon Ho and Bae, Hee Jin}, title = {End user searching: A Web log analysis of NAVER, a Korean Web search engine}, journal = {Library & Information Science Research}, year = {2005}, volume = {27}, number = {2}, pages = {203 - 221}, url = {http://www.sciencedirect.com/science/article/pii/S0740818805000083}, doi = {10.1016/j.lisr.2005.01.013}, issn = {0740-8188}, keywords = {mining, query, search, term, weblog}, abstract = {Transaction logs of NAVER, a major Korean Web search engine, were analyzed to track the information-seeking behavior of Korean Web users. These transaction logs include more than 40 million queries collected over 1 week. This study examines current transaction log analysis methodologies and proposes a method for log cleaning, session definition, and query classification. A term definition method which is necessary for Korean transaction log analysis is also discussed. The results of this study show that users behave in a simple way: they type in short queries with a few query terms, seldom use advanced features, and view few results' pages. Users also behave in a passive way: they seldom change search environments set by the system. It is of interest that users tend to change their queries totally rather than adding or deleting terms to modify the previous queries. The results of this study might contribute to the development of more efficient and effective Web search engines and services.} }

%0 = article %A = Park, Soyeon and Lee, Joon Ho and Bae, Hee Jin %D = 2005 %T = End user searching: A Web log analysis of NAVER, a Korean Web search engine %U = http://www.sciencedirect.com/science/article/pii/S0740818805000083

In the last decade, the importance of analyzing information management systems logs has grown, because log data constitute a relevant aspect in evaluating the quality of such systems. A review of 10 years of research on log analysis is presented in this paper. About 50 papers and posters from five major conferences and about 30 related journal papers have been selected to trace the history of the state-of-the-art in this field. The paper presents an overview of two main themes: Web search engine log analysis and Digital Library System log analysis. The problem of the analysis of different sources of log data and the distribution of data are investigated.

@article{agosti2012analysis, author = {Agosti, Maristella and Crivellari, Franco and Di Nunzio, GiorgioMaria}, title = {Web log analysis: a review of a decade of studies about information acquisition, inspection and interpretation of user interaction}, journal = {Data Mining and Knowledge Discovery}, publisher = {Springer US}, year = {2012}, volume = {24}, number = {3}, pages = {663-696}, url = {http://dx.doi.org/10.1007/s10618-011-0228-8}, doi = {10.1007/s10618-011-0228-8}, issn = {1384-5810}, keywords = {mining, review, weblog}, abstract = {In the last decade, the importance of analyzing information management systems logs has grown, because log data constitute a relevant aspect in evaluating the quality of such systems. A review of 10 years of research on log analysis is presented in this paper. About 50 papers and posters from five major conferences and about 30 related journal papers have been selected to trace the history of the state-of-the-art in this field. The paper presents an overview of two main themes: Web search engine log analysis and Digital Library System log analysis. The problem of the analysis of different sources of log data and the distribution of data are investigated.} }

%0 = article %A = Agosti, Maristella and Crivellari, Franco and Di Nunzio, GiorgioMaria %D = 2012 %I = Springer US %T = Web log analysis: a review of a decade of studies about information acquisition, inspection and interpretation of user interaction %U = http://dx.doi.org/10.1007/s10618-011-0228-8

We investigate tag and query logs to see if the terms people use to annotate websites are similar to the ones they use to query for them. Over a set of URLs, we compare the distribution of tags used to annotate each URL with the distribution of query terms for clicks on the same URL. Understanding the relationship between the distributions is important to determine how useful tag data may be for improving search results and conversely, query data for improving tag prediction. In our study, we compare both term frequency distributions using vocabulary overlap and relative entropy. We also test statistically whether the term counts come from the same underlying distribution. Our results indicate that the vocabulary used for tagging and searching for content are similar but not identical. We further investigate the content of the websites to see which of the two distributions (tag or query) is most similar to the content of the annotated/searched URL. Finally, we analyze the similarity for different categories of URLs in our sample to see if the similarity between distributions is dependent on the topic of the website or the popularity of the URL.

@inproceedings{carman2009statistical, author = {Carman, Mark J. and Baillie, Mark and Gwadera, Robert and Crestani, Fabio}, title = {A statistical comparison of tag and query logs}, booktitle = {Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval}, series = {SIGIR '09}, publisher = {ACM}, address = {New York, NY, USA}, year = {2009}, pages = {123--130}, url = {http://doi.acm.org/10.1145/1571941.1571965}, doi = {10.1145/1571941.1571965}, isbn = {978-1-60558-483-6}, keywords = {comparison, diagram, divergence, kullblack-Leibler, mining, tags, triangular, vocabulary, weblog}, abstract = {We investigate tag and query logs to see if the terms people use to annotate websites are similar to the ones they use to query for them. Over a set of URLs, we compare the distribution of tags used to annotate each URL with the distribution of query terms for clicks on the same URL. Understanding the relationship between the distributions is important to determine how useful tag data may be for improving search results and conversely, query data for improving tag prediction. In our study, we compare both term frequency distributions using vocabulary overlap and relative entropy. We also test statistically whether the term counts come from the same underlying distribution. Our results indicate that the vocabulary used for tagging and searching for content are similar but not identical. We further investigate the content of the websites to see which of the two distributions (tag or query) is most similar to the content of the annotated/searched URL. Finally, we analyze the similarity for different categories of URLs in our sample to see if the similarity between distributions is dependent on the topic of the website or the popularity of the URL.} }

%0 = inproceedings %A = Carman, Mark J. and Baillie, Mark and Gwadera, Robert and Crestani, Fabio %B = Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval %C = New York, NY, USA %D = 2009 %I = ACM %T = A statistical comparison of tag and query logs %U = http://doi.acm.org/10.1145/1571941.1571965

While recent progress has been achieved in understanding the structure and dynamics of social tagging systems, we know little about the underlying user motivations for tagging, and how they influence resulting folksonomies and tags. This paper addresses three issues related to this question. (1) What distinctions of user motivations are identified by previous research, and in what ways are the motivations of users amenable to quantitative analysis? (2) To what extent does tagging motivation vary across different social tagging systems? (3) How does variability in user motivation influence resulting tags and folksonomies? In this paper, we present measures to detect whether a tagger is primarily motivated by categorizing or describing resources, and apply these measures to datasets from seven different tagging systems. Our results show that (a) users’ motivation for tagging varies not only across, but also within tagging systems, and that (b) tag agreement among users who are motivated by categorizing resources is significantly lower than among users who are motivated by describing resources. Our findings are relevant for (1) the development of tag-based user interfaces, (2) the analysis of tag semantics and (3) the design of search algorithms for social tagging systems.

@article{strohmaier2012understanding, author = {Strohmaier, Markus and Körner, Christian and Kern, Roman}, title = {Understanding why users tag: A survey of tagging motivation literature and results from an empirical study}, journal = {Web Semantics: Science, Services and Agents on the World Wide Web}, year = {2012}, volume = {17}, number = {0}, pages = {1 - 11}, url = {http://www.sciencedirect.com/science/article/pii/S1570826812000820}, doi = {10.1016/j.websem.2012.09.003}, issn = {1570-8268}, keywords = {mining, motivation, survey, tagging, understanding, users, weblog}, abstract = {While recent progress has been achieved in understanding the structure and dynamics of social tagging systems, we know little about the underlying user motivations for tagging, and how they influence resulting folksonomies and tags. This paper addresses three issues related to this question. (1) What distinctions of user motivations are identified by previous research, and in what ways are the motivations of users amenable to quantitative analysis? (2) To what extent does tagging motivation vary across different social tagging systems? (3) How does variability in user motivation influence resulting tags and folksonomies? In this paper, we present measures to detect whether a tagger is primarily motivated by categorizing or describing resources, and apply these measures to datasets from seven different tagging systems. Our results show that (a) users’ motivation for tagging varies not only across, but also within tagging systems, and that (b) tag agreement among users who are motivated by categorizing resources is significantly lower than among users who are motivated by describing resources. Our findings are relevant for (1) the development of tag-based user interfaces, (2) the analysis of tag semantics and (3) the design of search algorithms for social tagging systems.} }

%0 = article %A = Strohmaier, Markus and Körner, Christian and Kern, Roman %D = 2012 %T = Understanding why users tag: A survey of tagging motivation literature and results from an empirical study %U = http://www.sciencedirect.com/science/article/pii/S1570826812000820

Popular online social networks (OSNs) like Facebook and Twitter are changing the way users communicate and interact with the Internet. A deep understanding of user interactions in OSNs can provide important insights into questions of human social behavior and into the design of social platforms and applications. However, recent studies have shown that a majority of user interactions on OSNs are latent interactions, that is, passive actions, such as profile browsing, that cannot be observed by traditional measurement techniques. In this article, we seek a deeper understanding of both active and latent user interactions in OSNs. For quantifiable data on latent user interactions, we perform a detailed measurement study on Renren, the largest OSN in China with more than 220 million users to date. All friendship links in Renren are public, allowing us to exhaustively crawl a connected graph component of 42 million users and 1.66 billion social links in 2009. Renren also keeps detailed, publicly viewable visitor logs for each user profile. We capture detailed histories of profile visits over a period of 90 days for users in the Peking University Renren network and use statistics of profile visits to study issues of user profile popularity, reciprocity of profile visits, and the impact of content updates on user popularity. We find that latent interactions are much more prevalent and frequent than active events, are nonreciprocal in nature, and that profile popularity is correlated with page views of content rather than with quantity of content updates. Finally, we construct latent interaction graphs as models of user browsing behavior and compare their structural properties, evolution, community structure, and mixing times against those of both active interaction graphs and social graphs.

@article{jiang2013understanding, author = {Jiang, Jing and Wilson, Christo and Wang, Xiao and Sha, Wenpeng and Huang, Peng and Dai, Yafei and Zhao, Ben Y.}, title = {Understanding Latent Interactions in Online Social Networks}, journal = {ACM Trans. Web}, publisher = {ACM}, address = {New York, NY, USA}, year = {2013}, volume = {7}, number = {4}, pages = {18:1--18:39}, url = {http://doi.acm.org/10.1145/2517040}, doi = {10.1145/2517040}, issn = {1559-1131}, keywords = {analyis, interaction, latent, log, mining, network, social, user, web}, abstract = {Popular online social networks (OSNs) like Facebook and Twitter are changing the way users communicate and interact with the Internet. A deep understanding of user interactions in OSNs can provide important insights into questions of human social behavior and into the design of social platforms and applications. However, recent studies have shown that a majority of user interactions on OSNs are latent interactions, that is, passive actions, such as profile browsing, that cannot be observed by traditional measurement techniques. In this article, we seek a deeper understanding of both active and latent user interactions in OSNs. For quantifiable data on latent user interactions, we perform a detailed measurement study on Renren, the largest OSN in China with more than 220 million users to date. All friendship links in Renren are public, allowing us to exhaustively crawl a connected graph component of 42 million users and 1.66 billion social links in 2009. Renren also keeps detailed, publicly viewable visitor logs for each user profile. We capture detailed histories of profile visits over a period of 90 days for users in the Peking University Renren network and use statistics of profile visits to study issues of user profile popularity, reciprocity of profile visits, and the impact of content updates on user popularity. We find that latent interactions are much more prevalent and frequent than active events, are nonreciprocal in nature, and that profile popularity is correlated with page views of content rather than with quantity of content updates. Finally, we construct latent interaction graphs as models of user browsing behavior and compare their structural properties, evolution, community structure, and mixing times against those of both active interaction graphs and social graphs.} }

%0 = article %A = Jiang, Jing and Wilson, Christo and Wang, Xiao and Sha, Wenpeng and Huang, Peng and Dai, Yafei and Zhao, Ben Y. %C = New York, NY, USA %D = 2013 %I = ACM %T = Understanding Latent Interactions in Online Social Networks %U = http://doi.acm.org/10.1145/2517040

We propose a system for mining videos from the web for supplementing the content of electronic textbooks in order to enhance their utility. Textbooks are generally organized into sections such that each section explains very few concepts and every concept is primarily explained in one section. Building upon these principles from the education literature and drawing upon the theory of

@incollection{agrawal2014mining, author = {Agrawal, Rakesh and Christoforaki, Maria and Gollapudi, Sreenivas and Kannan, Anitha and Kenthapadi, Krishnaram and Swaminathan, Adith}, title = {Mining Videos from the Web for Electronic Textbooks}, editor = {Glodeanu, CynthiaVera and Kaytoue, Mehdi and Sacarea, Christian}, booktitle = {Formal Concept Analysis}, series = {Lecture Notes in Computer Science}, publisher = {Springer International Publishing}, year = {2014}, volume = {8478}, pages = {219-234}, url = {http://dx.doi.org/10.1007/978-3-319-07248-7_16}, doi = {10.1007/978-3-319-07248-7_16}, isbn = {978-3-319-07247-0}, keywords = {application, fca, mining, video}, abstract = {We propose a system for mining videos from the web for supplementing the content of electronic textbooks in order to enhance their utility. Textbooks are generally organized into sections such that each section explains very few concepts and every concept is primarily explained in one section. Building upon these principles from the education literature and drawing upon the theory of } }

%0 = incollection %A = Agrawal, Rakesh and Christoforaki, Maria and Gollapudi, Sreenivas and Kannan, Anitha and Kenthapadi, Krishnaram and Swaminathan, Adith %B = Formal Concept Analysis %D = 2014 %I = Springer International Publishing %T = Mining Videos from the Web for Electronic Textbooks %U = http://dx.doi.org/10.1007/978-3-319-07248-7_16