Tagging Communities

From NetSysLab

Jump to: navigation, search

Characterizing and Harnessing Collaborative Tagging Communities

Web 2.0, the new wave of applications on the World Wide Web, brings new business opportunities and important research challenges. In this new paradigm, applications incorporate mechanisms that encourage the creation of online communities built around user-generated content. Today, millions of users form large scale online communities with different business models and functionalities that span from media sharing communities (e.g., Flickr, del.icio.us, YouTube, Blogger) to personal and collaborative knowledge management environments (e.g., Wikipedia, OpnTag, Connotea, CiteULike). From a business perspective, the popularity of such systems brings the potential of a vast market for online services, since users demonstrate an increasing interest in online tools that support their daily activities. The motivation that drives users to engage in online activities goes from a simple desire to share content (e.g., photos and videos) to active collaboration on content production and organization. In fact, companies are already coupling free Web 2.0 services with commercial offers. For instance, Flickr (http://www.flickr.com), with a user base of more than one million, has a growing list of tools and services provided by satellite companies that aim to convert Flickr users into consumers of their products. Although the existence of both business and research opportunities is clear, due to the relative youth of Web 2.0 systems and to their unique collaborative characteristics, little information is currently available to help companies exploring this new market efficiently. To fill this knowledge gap, this study will address two fundamental issues that are both industrially important and scientifically challenging:

Scalability: as the user population grows, services need to offer the same quality to maintain the system utility. Thus, this study aims to harness patterns in user behavior to address the side effects of the user population growth.

Spam: similarly to the previous generation of Web systems that was subject of malicious behavior, e.g., spam pages and techniques to manipulate search results, Web 2.0 is also a target for malicious users and spammers. The goal of this study is to assess the real impact spammers can have, and to design and evaluate countermeasures to cope with such misbehavior.

The key to address these two challenges is a good understanding of users’ behavior in online communities. Therefore, models that explain usage patterns in these communities are highly valuable to design new products or to improve existing services.

Publications

[12] Where are the 'key' words? Optimizing multimedia textual attributes to improve viewership, Tatiana Pontes, Elizeu Santos-Neto, Jussara M. Almeida, Matei Ripeanu, First Monday 20(3) (2015) pdf
[11] Reuse, Temporal Dynamics, Interest Sharing, and Collaboration in Social Tagging Systems, Elizeu Santos-Neto, David Condon, Nazareno Andrade, Adriana Iamnitchi, Matei Ripeanu, First Monday Magazine, 19(7) (2014) link TechnicalReport
[10] Assessing the Value of Peer-Produced Information for Exploratory Search, Elizeu Santos-Neto, Flavio Figueiredo, Nigini Oliveira, Nazareno Andrade, Jussara Almeida, Matei Ripeanu, TechnicalReport arXiv:1510.03004
[9] On the Choice of Data Sources to Improve Content Discoverability via Textual Feature Optimization, Elizeu Santos Neto, Tatiana Pontes, Jussara Almeida, Matei Ripeanu, ACM Hypertext Conference (HT'2014), Santiago de Chile, Chile, September 1-4, 2014. pdf slides
[8] Towards Boosting Video Popularity via Tag Selection, Elizeu Santos Neto, Tatiana Pontes, Jussara Almeida, Matei Ripeanu, ACM Workshop on Social Multimedia and Storytelling (SoMuS), April 2014, Glasgow pdf slides
[7] Characterizing and Harnessing Peer-Production of Information in Social Tagging Systems, Elizeu Santos-Neto, In the Proceedings of the 5th ACM International Conference on Web Search and Data Mining – Doctoral Consortium (WSDM 2012 Doctoral Consortium), Seattle, WA, USA, February 2012 pdf
[6] Assessing the Value of Contributions in Tagging Systems, Elizeu Santos-Neto, Flavio Figueiredo, Jussara Almeida, Miranda Mowbray, Marcos Gonçalves, Matei Ripeanu, Second IEEE International Conference on Social Computing (Symposium on Social Intelligence and Networking -- SIN'2010), Minneapolis, MN, August 2010 (acceptance rate 15%) doi pdf slides
[5] The Small World of File Sharing, Adriana Iamnitchi, Matei Ripeanu, Elizeu Santos-Neto, Ian Foster, IEEE Transactions on Parallel and Distributed Systems (accepted) pdf
[4] Individual and Social Behavior in Tagging Systems, Elizeu Santos-Neto, David Condon, Nazareno Andrade, Adriana Iamnitchi, Matei Ripeanu, In the 20th ACM Conference on Hypertext and Hypermedia (HT'09), Torino, Italy, July 2009. pdf
[3] Resource Demand and Supply in BitTorrent Content-Sharing Communities, Nazareno Andrade, Elizeu Santos-Neto, Francisco Brasileiro, Matei Ripeanu, Computer Networks, Volume 53, Issue 4, 18 March 2009 pdf doi
[2] Content Reuse and Shared Interest in Tagging Communities . Elizeu Santos-Neto, Matei Ripeanu, and Adriana Iamnitchi. AAAI 2008 Spring Symposia - Social Information Processing. Stanford, CA, USA, March 2008. abstractpdf
[1] Tracking User Attention in Collaborative Tagging Communities. Elizeu Santos-Neto, Matei Ripeanu, and Adriana Iamnitchi. International IEEE/ACM Workshop on Contextualized Attention Metadata (CAMA'07). Vancouver, BC, Canada, June 2007. abstractpdf