Towards Discovery of Influence and Personality Traits Through Social Link Prediction

Estimation of a person's influence and personality traits from social media data has many applications. We use social linkage criteria, such as number of followers and friends, as proxies to form corpora, from popular blogging site Livejournal, for examining two two-class classification problem...

Full description

Bibliographic Details
Main Authors: Nguyen, Thin, Phung, Dinh, Adams, Brett, Venkatesh, Svetha
Other Authors: Nicolas Nicolov
Format: Conference Paper
Published: IAAA 2011
Online Access:http://www.aaai.org/ocs/index.php/ICWSM/ICWSM11/paper/view/2772
http://hdl.handle.net/20.500.11937/21742
_version_ 1848750675138183168
author Nguyen, Thin
Phung, Dinh
Adams, Brett
Venkatesh, Svetha
author2 Nicolas Nicolov
author_facet Nicolas Nicolov
Nguyen, Thin
Phung, Dinh
Adams, Brett
Venkatesh, Svetha
author_sort Nguyen, Thin
building Curtin Institutional Repository
collection Online Access
description Estimation of a person's influence and personality traits from social media data has many applications. We use social linkage criteria, such as number of followers and friends, as proxies to form corpora, from popular blogging site Livejournal, for examining two two-class classification problems: influential vs. non-influential, and extraversion vs. introversion. Classification is performed using automatically-derived psycholinguistic and mood-based features of a user's textual messages. We experiment with three sub-corpora of 10000 users each, and present the most effective predictors for each category. The best classification result, at 80%, is achieved using psycholinguistic features; e.g., influentials are found to use more complex language, than non-influentials, and use more leisure-related terms.
first_indexed 2025-11-14T07:40:36Z
format Conference Paper
id curtin-20.500.11937-21742
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T07:40:36Z
publishDate 2011
publisher IAAA
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-217422023-01-27T05:26:32Z Towards Discovery of Influence and Personality Traits Through Social Link Prediction Nguyen, Thin Phung, Dinh Adams, Brett Venkatesh, Svetha Nicolas Nicolov James G. Shanahan Estimation of a person's influence and personality traits from social media data has many applications. We use social linkage criteria, such as number of followers and friends, as proxies to form corpora, from popular blogging site Livejournal, for examining two two-class classification problems: influential vs. non-influential, and extraversion vs. introversion. Classification is performed using automatically-derived psycholinguistic and mood-based features of a user's textual messages. We experiment with three sub-corpora of 10000 users each, and present the most effective predictors for each category. The best classification result, at 80%, is achieved using psycholinguistic features; e.g., influentials are found to use more complex language, than non-influentials, and use more leisure-related terms. 2011 Conference Paper http://hdl.handle.net/20.500.11937/21742 http://www.aaai.org/ocs/index.php/ICWSM/ICWSM11/paper/view/2772 IAAA restricted
spellingShingle Nguyen, Thin
Phung, Dinh
Adams, Brett
Venkatesh, Svetha
Towards Discovery of Influence and Personality Traits Through Social Link Prediction
title Towards Discovery of Influence and Personality Traits Through Social Link Prediction
title_full Towards Discovery of Influence and Personality Traits Through Social Link Prediction
title_fullStr Towards Discovery of Influence and Personality Traits Through Social Link Prediction
title_full_unstemmed Towards Discovery of Influence and Personality Traits Through Social Link Prediction
title_short Towards Discovery of Influence and Personality Traits Through Social Link Prediction
title_sort towards discovery of influence and personality traits through social link prediction
url http://www.aaai.org/ocs/index.php/ICWSM/ICWSM11/paper/view/2772
http://hdl.handle.net/20.500.11937/21742