Featured Articles

Featured Articles is a section of the Special Technical Community on Social Networks that will shed light to pieces of social network research that are considered interesting and promising. Each month one research article will be selected from the IEEE Computer Society Digital Library to be featured in this section. The content featured here will be curated by Symeon Papadopoulos. Eventually, the featured articles will become freely available from this page.

February 2015: Using Twitter Sentiment to Forecast the 2013 Pakistani Election and the 2014 Indian Election

posted Feb 18, 2015, 10:55 AM by Symeon Papadopoulos

Vadim Kagan, Andrew Stevens, V.S. Subrahmanian, "Using Twitter Sentiment to Forecast the 2013 Pakistani Election and the 2014 Indian Election", IEEE Intelligent Systems, vol.30, no. 1, pp. 2-5, Jan.-Feb. 2015, doi:10.1109/MIS.2015.16

Abstract: This column discusses the authors' efforts to project the winner of the 2013 Pakistan and the 2014 Indian prime minister election using social network analysis and methods to create a diffusion estimation model.

January 2015: Recommending Venues Using Continuous Predictive Social Media Analytics

posted Jan 19, 2015, 8:36 AM by Symeon Papadopoulos

Marco Balduini, Alessandro Bozzon, Emanuele Della Valle, Yi Huang, Geert-Jan Houben, "Recommending Venues Using Continuous Predictive Social Media Analytics", IEEE Internet Computing, vol.18, no. 5, pp. 28-35, Sept.-Oct. 2014, doi:10.1109/MIC.2014.84

Abstract: The authors' Continuous Predictive Social Media Analytics system operates in real time on social media streams and graphs to recommend venues to visitors of geo- and temporally bounded city-scale events. By combining deductive and inductive stream reasoning techniques with visitor-modeling functionalities, this system semantically analyzes and links visitors' social network activities to produce high-quality link predictions when information about preferences is sparse. The authors demonstrate their system's quality with experiments on real-world data.

December 2014: Computational Social Science for the World Wide Web

posted Dec 10, 2014, 8:46 AM by Symeon Papadopoulos

Markus Strohmaier, Claudia Wagner, "Computational Social Science for the World Wide Web", IEEE Intelligent Systems, vol.29, no. 5, pp. 84-88, Sept.-Oct. 2014, doi:10.1109/MIS.2014.80

Abstract: In introducing the field of computational social science to the intelligent systems community, the authors discuss how this field can help advance the current state of understanding and engineering social-computational systems on the World Wide Web.

November 2014: Trust and Privacy Exploitation in Online Social Networks

posted Nov 11, 2014, 4:03 AM by Symeon Papadopoulos

Kaze Wong, Angus Wong, Alan Yeung, Wei Fan, Su-Kit Tang, "Trust and Privacy Exploitation in Online Social Networks", IT Professional, vol.16, no. 5, pp. 28-33, Sept.-Oct. 2014, doi:10.1109/MITP.2014.79

Abstract: Online social networks have been typically created for convenience -so they haven't been built from the ground up with security in mind. They often have confusing privacy settings and are susceptible to various kinds of attacks that exploit users' trust and privacy. In this article, the authors discuss security pitfalls in today's social networks, briefly introducing common attack methods. They implemented a proof-of-concept Facebook app, which is actually a harmless malware that uses common attack methods to demonstrate the vulnerability of online social networks. Although today's online social networks commonly offer users a variety of security settings, users tend to trust the information obtained from online social networks regardless of the settings. This kind of user mentality can be more crucial than technical aspects in determining the level of security in online social networks.

October 2014: Predicting Edge Signs in Social Networks Using Frequent Subgraph Discovery

posted Oct 11, 2014, 1:58 PM by Symeon Papadopoulos

Athanasios Papaoikonomou, Magdalini Kardara, Konstantinos Tserpes, Theodora A. Varvarigou, "Predicting Edge Signs in Social Networks Using Frequent Subgraph Discovery", IEEE Internet Computing, vol.18, no. 5, pp. 36-43, Sept.-Oct. 2014, doi:10.1109/MIC.2014.82

Abstract: In signed social networks, users are connected via directional signed links that indicate their opinions about each other. Predicting the signs of such links is crucial for many real-world applications, such as recommendation systems. The authors mine patterns that emerge frequently in the social graph, and show that such patterns possess enough discriminative power to accurately predict the relationships among social network users. They evaluate their approach through an experimental study that comprises three large-scale, real-world datasets and show that it outperforms state-of-the art methods.

September 2014: Real-Time Crisis Mapping of Natural Disasters Using Social Media

posted Sep 11, 2014, 11:05 AM by Symeon Papadopoulos

Stuart E. Middleton, Lee Middleton, Stefano Modafferi, "Real-Time Crisis Mapping of Natural Disasters Using Social Media," IEEE Intelligent Systems, vol. 29, no. 2, pp. 9-17, Mar.-Apr. 2014, doi:10.1109/MIS.2013.126

Abstract: The proposed social media crisis mapping platform for natural disasters uses locations from gazetteer, street map, and volunteered geographic information (VGI) sources for areas at risk of disaster and matches them to geoparsed real-time tweet data streams. The authors use statistical analysis to generate real-time crisis maps. Geoparsing results are benchmarked against existing published work and evaluated across multilingual datasets. Two case studies compare five-day tweet crisis maps to official post-event impact assessment from the US National Geospatial Agency (NGA), compiled from verified satellite and aerial imagery sources.

August 2014: Toward Multiscreen Social TV with Geolocation-Aware Social Sense

posted Aug 19, 2014, 2:41 AM by Symeon Papadopoulos

Han Hu, Yonggang Wen, Huanbo Luan, Tat-Seng Chua, Xuelong Li, "Toward Multiscreen Social TV with Geolocation-Aware Social Sense," IEEE Multimedia, vol. 21, no. 3, pp. 10-19, July-Sept. 2014, doi:10.1109/MMUL.2014.2

Abstract: The increasing popularity of social interactions and geotagged, user-generated content has transformed the television viewing experience from laid-back video watching behavior into a "lean-forward"' socially engaged experience. This article describes a multiscreen, social TV system integrated with social sense via a second screen as a novel paradigm for content consumption. This new application is built upon the authors' cloud-centric media platform, which provides on-demand virtual machines for content platform services, including media distribution, storage, and processing. The media platform is also integrated with a Big Data social platform that crawls and mines social data related to the media content. Specifically, this new social TV approach consists of three key subsystems: interactive TV, social sense, and multiscreen orchestration. Interactive TV implements a cloud-based, social TV system, offering rich social features; social sense discovers the geolocation-aware public perception and knowledge related to the media content; and multiscreen orchestration provides an intuitive and user-friendly human-computer interface to combine the two other subsystems, fusing the TV viewing experience with social perception. The authors have built a proof-of-concept demo over a private cloud at the Nanyang Technological University (NTU), Singapore. Feature verification and performance comparisons demonstrate the feasibility and effectiveness of the proposed approach in transforming the TV viewing experience.

July 2014: Mining Urban Deprivation from Foursquare

posted Jul 10, 2014, 9:23 AM by Symeon Papadopoulos

Daniele Quercia, Diego Saez, "Mining Urban Deprivation from Foursquare: Implicit Crowdsourcing of City Land Use," IEEE Pervasive Computing, vol. 13, no. 2, pp. 30-36, Apr.-June. 2014, doi:10.1109/MPRV.2014.31

Abstract: Research has shown a relationship between the physical characteristics of a city neighborhood (such as the presence of playgrounds and fast-food outlets) and neighborhood deprivation as defined in socioeconomic indices. Official land-use data has often been the source for such research. This article examines the viability of using social-networking data as an alternative source. The authors study all venues on the Foursquare location-mapping application across a variety of London census areas. They study the relationship between the presence of different venues in an area and its score on the socioeconomic Index of Multiple Deprivation. They conclude that knowing which venues are hosted by which community offers not only insights into neighborhood deprivation but also a reasonable way of predicting community deprivation scores at fine-grained temporal resolutions. This article is part of a special issue on pervasive analytics and citizen science.

June 2014: Social Multimedia Crawling for Mining and Search

posted Jun 10, 2014, 10:25 AM by Symeon Papadopoulos

Symeon Papadopoulos, Yiannis Kompatsiaris, "Social Multimedia Crawling for Mining and Search," Computer, vol. 47, no. 5, pp. 84-87, May 2014, doi:10.1109/MC.2014.135

Abstract: Social multimedia can be leveraged for a wide range of applications, but mining and search systems require innovative crawling solutions to meet both technical and policy-related obstacles.

May 2014: A Tale of Three Social Networks

posted May 16, 2014, 11:09 AM by Symeon Papadopoulos

Pinghui Wang, Wenbo He, Junzhou Zhao, "A Tale of Three Social Networks: User Activity Comparisons across Facebook, Twitter, and Foursquare," IEEE Internet Computing, vol. 18, no. 2, pp. 10-15, Mar.-Apr. 2014, doi:10.1109/MIC.2013.128

Abstract: Despite recent efforts to characterize online social network (OSN) structures and activities, user behavior across different OSNs has received little attention. Yet such information could provide insight into issues relating to personal privacy protection. For instance, many Foursquare users reveal their Facebook and Twitter accounts to the public. The authors' in-depth measurement study examines users' network activities and privacy settings across Facebook, Twitter, and Foursquare. Results show that user activities are highly correlated among these three OSNs, which causes information leakage for a large fraction of Foursquare users.

1-10 of 35