Social Media Mood Prediction with Emotional Exploration and Personality Traits
Project Overview
With the mature development of the Internet and virtual communities, how to accurately analyze potential and future development trends from the massive document data of online communities will be an important emerging topic in the field of humanities and social sciences.
Therefore, in the first year of this project, we hope to use innovative big data and Sentiment Mining algorithms, combined with the Big Five Personality Traits, to classify the massive number of articles in Facebook communities based on personality traits and the articles they belong to. In the second year, this project will build a classification model to conduct article sentiment identification, and then conduct performance evaluation to verify the experimental results. Finally, this project will adopt the Time Series perspective and use the Survival Analysis to analyze the public emotion and reactions of Taiwanese people to specific financial issues in real time, and explore whether the public emotion of virtual communities has a time series lag effect on subsequent specific events.
Source: Wikimedia Commons
