Identifying Themes in Social Media and Detecting Sentiments

Abstract

Recently, a huge wave of social media has generated significant impact in people's perceptions about technological domains. They are captured in several blogs/forums, where the themes relate to products of several companies. One of the companies can be interested to track them as resources for customer perceptions and detect user sentiments. The keyword-based approaches for identifying such themes fail to give satisfactory level of accuracy. Here, we address the above problems using statistical text-mining of blog entries. The crux of the analysis lies in mining quantitative information from textual entries. Once the relevant blog entries for the company/its competitors are filtered out, the theme identification is performed using a highly accurate novel technique termed as 'Best Separators Algorithm'. Logistic regression coupled with dimension reduction technique (singular value decomposition) is used to identify the tonality of those blogs. The final analysis shows significant improvement in terms of accuracy over popular approaches.

On the Socialness of Software

“…It provides facilities for users for instance to request new features or modifications, give social feedback on existing proposals, report errors, or externalize their experience with the system. 10 http://www.facebook.com/Office…”

“…Glance et al [3] visualize the popularity of blog topics over time and show a correlation with real world trends. Pal et al investigate the identification of themes and sentiments in social media by use of social network analysis and data mining [10]. We propose to exploit these results and mining techniques to communities of software applications and predict trends in application domains.…”

Customer Interaction Management with SCM

“…Since blogs consist of news or messages dealing with various topics, blog content has to be divided into several topic clusters. Pal and Saha (see [3]) from Hewlett Packard developed the "Best Separators Algorithm" which cuts documents into blocks according to theme relevance.…”