Mood State and Behavior Predictions in Social Media through Unstructured Data Analysis

Main Article Content

Gurpreet Singh Bawa
Suresh Kumar Sharma
Kanchan K. Jain


For mood State and Behavior Predictions in Social Media through Unstructured Data Analysis, a new model, Behavior Dirichlet Probability Model (BDPM), which can capture the Behavior and Mood of user on Social media is proposed using Dirichlet distribution. There is a colossal amount of data being generated regularly on social media in the form of text from various channels by individuals in the form of posts, tweets, status, comments, blogs, reviews etc. Most of it belongs to some conversation where real-world individuals discuss, analyze, comment, exchange information. Deriving personality traits from textual data can be useful in observing the underlying attributes of the author’s personality which might explain a lot about their behavior, traits etc. These insights of the individual can be utilized to obtain a clear picture of their personality and accordingly a variety of services, utilities would follow automatically. Using Dirichlet probability distribution, the aim is to estimate the probability of each personality trait (or mood state) for an author and then model the latent features in the text which are not captured by the BDPM. As a result, the study can be helpful in prediction of mood state/personality trait as well as capturing the significance of the latent features apart from the ones present in the taxonomies, which will help in making an improved mood state or personality prediction.

Personality trait, behavior predictions, mood state prediction, dirichlet distribution, linguistic features.

Article Details

How to Cite
Bawa, G. S., Sharma, S. K., & Jain, K. K. (2019). Mood State and Behavior Predictions in Social Media through Unstructured Data Analysis. Asian Journal of Probability and Statistics, 4(3), 1-9.
Original Research Article


Pennebaker JW, King LA. Linguistic styles: Language use as an individual difference. Journal of Personality and Social Psychology. 1999;77:1296–1312.

Coltheart M. The MRC psycholinguistic database. Quarterly Journal of Experimental Psychology. 1981;33A:497–505.

Pennebaker JW, Francis ME, Booth RJ. Inquiry and Word Count: LIWC 2001. Lawrence Erlbaum, Mahwah, NJ; 2001.

Heylighen F, Dewaele JM. Variation in the contextuality of language: An empirical measure. Context in Context, Special issue of Foundations of Science. 2002;7(3):293–340.