%0 Journal Article %1 citeulike:13992657 %A Li, Lin %A Li, Ang %A Hao, Bibo %A Guan, Zengda %A Zhu, Tingshao %D 2014 %I Public Library of Science %J PLoS ONE %K individual-differences log-mining personal-traits %N 1 %P e84997+ %R 10.1371/journal.pone.0084997 %T Predicting Active Users' Personality Based on Micro-Blogging Behaviors %U http://dx.doi.org/10.1371/journal.pone.0084997 %V 9 %X Because of its richness and availability, micro-blogging has become an ideal platform for conducting psychological research. In this paper, we proposed to predict active users' personality traits through micro-blogging behaviors. 547 Chinese active users of micro-blogging participated in this study. Their personality traits were measured by the Big Five Inventory, and digital records of micro-blogging behaviors were collected via web crawlers. After extracting 845 micro-blogging behavioral features, we first trained classification models utilizing Support Vector Machine (SVM), differentiating participants with high and low scores on each dimension of the Big Five Inventory. The classification accuracy ranged from 84\% to 92\%. We also built regression models utilizing PaceRegression methods, predicting participants' scores on each dimension of the Big Five Inventory. The Pearson correlation coefficients between predicted scores and actual scores ranged from 0.48 to 0.54. Results indicated that active users' personality traits could be predicted by micro-blogging behaviors.

@article{citeulike:13992657, abstract = {{Because of its richness and availability, micro-blogging has become an ideal platform for conducting psychological research. In this paper, we proposed to predict active users' personality traits through micro-blogging behaviors. 547 Chinese active users of micro-blogging participated in this study. Their personality traits were measured by the Big Five Inventory, and digital records of micro-blogging behaviors were collected via web crawlers. After extracting 845 micro-blogging behavioral features, we first trained classification models utilizing Support Vector Machine (SVM), differentiating participants with high and low scores on each dimension of the Big Five Inventory. The classification accuracy ranged from 84\% to 92\%. We also built regression models utilizing PaceRegression methods, predicting participants' scores on each dimension of the Big Five Inventory. The Pearson correlation coefficients between predicted scores and actual scores ranged from 0.48 to 0.54. Results indicated that active users' personality traits could be predicted by micro-blogging behaviors.}}, added-at = {2017-11-15T17:02:25.000+0100}, author = {Li, Lin and Li, Ang and Hao, Bibo and Guan, Zengda and Zhu, Tingshao}, biburl = {https://www.bibsonomy.org/bibtex/21bde5ebfd4ae5f2b6fe9c5ece3b29e0f/brusilovsky}, citeulike-article-id = {13992657}, citeulike-linkout-0 = {http://dx.doi.org/10.1371/journal.pone.0084997}, day = 22, doi = {10.1371/journal.pone.0084997}, interhash = {85c49d5d4c918a7a29a9b1e24f4993c8}, intrahash = {1bde5ebfd4ae5f2b6fe9c5ece3b29e0f}, journal = {PLoS ONE}, keywords = {individual-differences log-mining personal-traits}, month = jan, number = 1, pages = {e84997+}, posted-at = {2016-04-01 18:41:44}, priority = {2}, publisher = {Public Library of Science}, timestamp = {2023-06-27T10:45:56.000+0200}, title = {{Predicting Active Users' Personality Based on Micro-Blogging Behaviors}}, url = {http://dx.doi.org/10.1371/journal.pone.0084997}, volume = 9, year = 2014 }