Abstract
Recently numerous studies are conducted to estimate the human personality from theonline social activities. This paper develops a comprehensive model for political attitude estimationleveraging the Facebook Like information of the users. We designed a Facebook Crawler that efficientlycollects data overcoming the difficulties in crawling Ajax enabled Facebook pages. We show thatthe category level selection can reduce the data analysis complexity utilizing the sparsity of the hugelike-attitude matrix. In the Korean Facebook users’ context, only 28 criteria (3% of the total) canestimate the political polarity of the user with high accuracy (AUC of 0.82).
| Translated title of the contribution | A Study on Political Attitude Estimation of Korean OSN Users |
|---|---|
| Original language | Korean |
| Pages (from-to) | 1-11 |
| Number of pages | 11 |
| Journal | 한국산업정보학회논문지 |
| Volume | 21 |
| Issue number | 4 |
| DOIs | |
| State | Published - Aug 2016 |