Conference Paper

Web Science 2.0: Identifying Trends through Semantic Social Network Analysis

DOI: 10.2139/ssrn.1299869 Conference: IEEE Conference on Social Computing (SocialCom-09)
Source: DBLP

ABSTRACT We introduce a novel set of social network analysis based algorithms for mining the Web, blogs, and online forums to identify trends and find the people launching these new trends. These algorithms have been implemented in Condor, a software system for predictive search and analysis of the Web and especially social networks. Algorithms include the temporal computation of network centrality measures, the visualization of social networks as Cybermaps, a semantic process of mining and analyzing large mounts of text based on social network analysis, and sentiment analysis and information filtering methods. The temporal calculation of betweenness of concepts permits to extract and predict long-term trends on the popularity of relevant concepts such as brands, movies, and politicians. We illustrate our approach by qualitatively comparing Web buzz and our Web betweenness for the 2008 US presidential elections, as well as correlating the Web buzz index with share prices.

0 Bookmarks
 · 
130 Views
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The growing usage of internet and social media by a wider audience of citizens sharply increases the possibility to investigate the web as a device to explore and track their (policy) preferences. In the present paper we apply the recent method proposed by Hopkins and King (2010) to three very different scenarios, by tracking on one side the on-line popularity of Italian political leaders throughout 2011, and on the other side the voting intention of French internet-users in both the 2012 Presidential ballot and in the subsequent Legislative election. The variety of contexts so analyzed has been deliberately pursued to better investigate the strength and the limits of monitor-ing social networks, as well as to assess which factors can increase (or decrease) their reliability. Despite internet users are not necessarily representative of the whole pop-ulation of countrys citizens, our analysis shows a remarkable ability of social-media to forecast electoral results as well as a consistent correlation between social-media results and the ones we obtain from more traditional mass surveys. Still, sentiment analysis of social network seems to provide more accurate predictions when focusing on the most popular leaders or on 'mainstream' parties, while both traditional sur-veys as well as social networks analyses methods appear to be affected, at least in part, by the same sources of bias, like the strategic behavior and the spiral of silence. Finally, the possibility of an 'information overload' arises as a further factor affecting negatively the analysis of social-media.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This research analyzes Muslim nation (MN) networks associated with Jihad for the previous two years. We captured all documents from Lexis-Nexis Academic's BBC International Monitoring - which contains translated transcriptions of web pages, broadcasts, newspapers, and other content - for each of 47 Muslim nations (MNs) using the search term: jihad and MN name. We presented a new kind of semantic network time series analysis of this text. Unlike most semantic network analysis, our nodes were time segments, not words. The link strengths were similarity scores of time nodes across 779,192 word pairs. The time nodes were 105 weekly intervals. We created a two-mode matrix. Columns were the frequencies of time slices' word pairs, appearing in a three-word window. Matrix rows were three-quarters of a million word pairs extracted from the aggregate two-year text file. We converted this two-mode matrix to a one-mode matrix by computing the similarity of each pair of time slices across the rows of word pairs. This resulted in a one-mode network of 105 by 105 time units. Pearson correlations were the similarity coefficients. We conducted social network analysis of the time nodes to find the most central ones. Highly central nodes lie more often on the shortest paths between all pairs of time nodes. They therefore contain in their internal lists of highest frequency word pairs the main themes across the two-years of text. The method is highly automated and efficient. In this case only three central nodes provided the basis for an analyst's interpretations of main propaganda themes.
    Intelligence and Security Informatics Conference (EISIC), 2012 European; 01/2012
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper considers the extraction and analysis of Social Networks for the identification of trends. Our methodology focuses on the utilization of semantics for determination of relevant networks within unstructured data. The Social Networks are examined from the perspective of structure and considered as a time series. Our metrics focus on the identification of influence and power among key players. This method is applied against a collection of Twitter messages and compared to historical market share trends of technologically-related topics. Through this work we demonstrate that structural qualities reflecting community dynamics can provide insight to the prediction of long-term trends. The goal of this work is to lend insight to the characterization of consumer behavior, particularly in the area of technology forecasting.
    Semantic Computing (ICSC), 2012 IEEE Sixth International Conference on; 01/2012

Full-text (3 Sources)

Download
110 Downloads
Available from
Jun 3, 2014