Leveraging Textual Sentiment Analysis with Social Network Modelling

MyBook is a cheap paperback edition of the original book and will be sold at uniform, low price.
This Chapter is currently unavailable for purchase.

Automatic computational analysis of political texts poses major challenges for state-of-the-art Sentiment Analysis and Natural Language Processing tools. In this initial study, we investigate the feasibility of combining purely linguistic indicators of political sentiment with non-linguistic evidence gained from concomitant social network analysis. The analysis draws on a corpus of 2.8 million political blog posts by 16,741 bloggers. We focus on modeling blogosphere sentiment centered around Barack Obama during the 2008 U.S. presidential election, and describe a series of initial sentiment classification experiments on a data set of 700 crowd-sourced posts labeled for attitude with respect to Obama. Our approach employs a hybrid machine-learning and logic-based framework which operates along three distinct levels of analysis encompassing standard shallow document classification, deep linguistic multi-entity sentiment analysis and scoring and social network modeling. The initial results highlight the inherent complexity of the classification task and point towards the positive effects of learning features that exploit entity-level sentiment and social-network structure.


This is a required field
Please enter a valid email address