Predicting Personality from Social Media Text

Citation data:

AIS Transactions on Replication Research, Vol: 2, Issue: 1, Page: 1-10

Publication Year:
2016
Usage 1773
Downloads 1515
Abstract Views 258
Repository URL:
http://aisel.aisnet.org/trr/vol2/iss1/2
DOI:
10.17705/1atrr.00009
Author(s):
Golbeck, Jennifer Ann
Publisher(s):
Association for Information Systems
Tags:
social media; personality; replication; psycholinguistics; Management Information Systems
article description
This paper replicates text-based Big Five personality score predictions generated by the Receptiviti API—a tool built on and tied to the popular psycholinguistic analysis tool Linguistic Inquiry and Word Count (LIWC). We use four social media datasets with posts and personality scores for nearly 9,000 users to determine the accuracy of the Receptiviti predictions. We found Mean Absolute Error rates in the 15–30% range, which is a higher error rate than other personality prediction algorithms in the literature. Preliminary analysis suggests relative scores between groups of subjects may be maintained, which may be sufficient for many applications.