Investigation of Opinion Polarization in Online Communication: Towards an Integration of Explanation and Prediction
| Project/Area Number |
22K20182
|
|---|
| Research Category |
Grant-in-Aid for Research Activity Start-up
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
0108:Sociology and related fields
|
|---|
| Research Institution | Tohoku University (2023)
The University of Tokyo (2022) |
|---|
Principal Investigator |
呂 沢宇 東北大学, 文学研究科, 准教授 (30966312)
|
|---|
| Project Period (FY) |
2022-08-31 – 2024-03-31
|
| Project Status |
Completed (Fiscal Year 2023)
|
| Budget Amount *help |
¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
Fiscal Year 2023: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2022: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 計算社会科学 / 分極化 / ソーシャルメディア / ビッグデータ解析 / 機械学習 |
|---|
| Outline of Research at the Start |
Based on a computational social science framework, the research sets out to explore the causal mechanism and construct a predictive model of opinion polarization in online communication.
|
| Outline of Annual Research Achievements |
(1) This project uses big data data and computational methods to detect the expressed opinion on social media. We find the individuals’ tendency to maintain their partisan identification can lead to hostility toward individuals of opposing partisans, serving as a potential mechanism that contributes to polarization.
(2) This project explores the possibilities of LLMs (Large Language Models) in research related to opinion polarization. We have validated and demonstrated that LLMs can, through prompts, mimic individuals with specific partisan leanings and cognitive biases. This implies that LLMs can be used in social simulations to enrich the fidelity and complexity of simulations, potentially yielding deeper insights into the mechanisms of opinion polarization.
|
Report
(2 results)
Research Products
(7 results)
