Home Linguistics & Semiotics Leveraging Textual Sentiment Analysis with Social Network Modelling
Chapter
Licensed
Unlicensed Requires Authentication

Leveraging Textual Sentiment Analysis with Social Network Modelling

Sentiment Analysis of Political Blogs in the 2008 U.S. Presidential Election
  • Wojciech Gryc and Karo Moilanen
View more publications by John Benjamins Publishing Company
To Publisher Page
From Text to Political Positions
This chapter is in the book From Text to Political Positions

Abstract

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.

Abstract

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.

Chapters in this book

  1. Prelim pages i
  2. Table of contents v
  3. Foreword vii
  4. Positions of Parties and Political Cleavages between Parties in Texts 1
  5. PART I. Computational Methods for Political Text Analysis
  6. PART I: Introduction 23
  7. Comparing the Position of Canadian Political Parties using French and English Manifestos as Textual Data 27
  8. Leveraging Textual Sentiment Analysis with Social Network Modelling 47
  9. Issue Framing and Language Use in the Swedish Blogosphere 71
  10. Text to Ideology or Text to Party Status? 93
  11. Sentiment Analysis in Parliamentary Proceedings 117
  12. The Qualitative Analysis of Political Documents 135
  13. PART II. From Text to Political Positions via Discourse Analysis
  14. PART II: Introduction 163
  15. The Potential of Narrative Strategies in the Discursive Construction of Hegemonic Positions and Social Change 171
  16. Christians, Feminists, Liberals, Socialists, Workers and Employers 189
  17. Between Union and a United Ireland 207
  18. Systematic Stylistic Analysis 225
  19. Participation and recontextualisation in New Media 245
  20. PART III. Converging methods
  21. PART III: Introduction 271
  22. From Text to the Construction of Political Party Landscapes 275
  23. From Text to Political Positions 297
  24. About the authors 325
  25. Index 331
https://doi.org/10.1075/dapsac.55.03gry

Chapters in this book

  1. Prelim pages i
  2. Table of contents v
  3. Foreword vii
  4. Positions of Parties and Political Cleavages between Parties in Texts 1
  5. PART I. Computational Methods for Political Text Analysis
  6. PART I: Introduction 23
  7. Comparing the Position of Canadian Political Parties using French and English Manifestos as Textual Data 27
  8. Leveraging Textual Sentiment Analysis with Social Network Modelling 47
  9. Issue Framing and Language Use in the Swedish Blogosphere 71
  10. Text to Ideology or Text to Party Status? 93
  11. Sentiment Analysis in Parliamentary Proceedings 117
  12. The Qualitative Analysis of Political Documents 135
  13. PART II. From Text to Political Positions via Discourse Analysis
  14. PART II: Introduction 163
  15. The Potential of Narrative Strategies in the Discursive Construction of Hegemonic Positions and Social Change 171
  16. Christians, Feminists, Liberals, Socialists, Workers and Employers 189
  17. Between Union and a United Ireland 207
  18. Systematic Stylistic Analysis 225
  19. Participation and recontextualisation in New Media 245
  20. PART III. Converging methods
  21. PART III: Introduction 271
  22. From Text to the Construction of Political Party Landscapes 275
  23. From Text to Political Positions 297
  24. About the authors 325
  25. Index 331
Sign up now to receive a 20% welcome discount
Institutional Access
How does access work?
Have an idea on how to improve our website?
Please write us.
© 2026 De Gruyter Brill
Downloaded on 10.2.2026 from https://www.degruyterbrill.com/document/doi/10.1075/dapsac.55.03gry/html
Scroll to top button