Mining The Blogosphere From A Socio-political Perspective

Summary: Blogs are websites that allow one or more individuals to write about things they want to share with others. The universe of all blog sites is referred to as Blogosphere. The ease & simplicity of creating blog posts and their free form and unedited nature have made the blogosphere a rich and unique source of data, which has attracted people and companies across disciplines to exploit it for varied purposes. The valuable data contained in posts from a large number of users across geographic, demographic and cultural boundaries provide a rich data source not only for commercial exploitation but also for psychological & sociopolitical research. This paper tries to demonstrate the plausibility of the idea through our clustering and opinion mining experiment on analysis of blog posts on recent socio-political developments in the new democratic republic of Nepal; and to elaborate the broader technical framework & tools required for this kind of analysis.

Motivation: Blogs have become a very popular medium for expressing opinions, communicating with others, providing suggestions, sharing thoughts on different issues and also to debate over them. The large amount of valuable data contained in the blogosphere is making it an important field of research, not only for academicians but also for people from industry and other disciplines. The study of blogosphere has helped in reshaping business models, assist viral marketing, providing trend analysis & sales prediction, and aiding counter terrorism efforts. The blogosphere is an ideal platform from which we can extract information, opinion, moods and emotions on various topics. It may include topics like political issues, social issues, product reviews or market surveys. The current research in blogosphere includes areas like blog classification and clustering, community discovery, analysis of relationship among bloggers, topic discovery & tagging, blog mining, trend discovery, bloggers’ sentiment & interest analysis, filtering spam blogs and modeling the blogosphere.

Most of the contemporary analytical research in blog mining, however, focuses more on marketing applications. Efforts on socio-political exploitation of the blogosphere are almost negligent. The fact that the content of the blogs are original free-form writings, and that they are very contemporary & emotion laden; makes the blogosphere an ideal platform for socio-political analysis. The personality, expertise, views and moods of bloggers are well reflected in their posts. The postings are on real time basis and information in the posts is current and relevant. It is, therefore, beyond doubt that the blogosphere now depicts the accurate views and sentiments of the common people, in an electronic media.

Main Contributions: In this paper, we have tried to analyze the blogosphere from a socio-political perspective by collecting and analyzing the blog posts about political and constitutional developments in the new democratic republic of Nepal.

Conclusion: Blogosphere has immense potential for socio-political studies and research, which needs to be exploited in a useful manner. The first hand, un-edited, free-form writings of bloggers provide an incomparable input data. The geographical, demographic and cultural diversity of the bloggers make the data still more valuable, and rich in the various perspectives of the topic of concern. Most of the contemporary work on blogosphere analysis (primarily for commercial exploitation), however, is limited to syntactic mechanisms. The textual nature of the blog data and the lack of sophisticated natural language processing tools (having semantic orientation), make the task very challenging. Availability of good text mining and language processing tools will definitely make the analysis results much more valuable. Moreover, with new structuring and semantic representations becoming popular on the World Wide Web, much of the limitations may be overcome and analytical experiment of this kind may produce more accurate results and hence more relevant inferences.

Download the papers from here:

research-paper      and          research-paper

Singh, V.K. ; Adhikari, R. ; Mahata, D. 
Computational Intelligence and Computing Research (ICCIC), 2010 IEEE International Conference on 

Digital Object Identifier: 10.1109/ICCIC.2010.5705807 
Publication Year: 2010 , Page(s): 1 – 4


Computational Intelligence and Computing Research (ICCIC), 2010 IEEE International Conference on 
Digital Object Identifier: 10.1109/ICCIC.2010.5705807 
Publication Year: 2010 , Page(s): 1 – 4


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s