Pre-HLSA: Predicting home location for Twitter users based on sentimental analysis

Abstract

Identifying the home location of Twitter users is very important in many business community applications. Therefore, many approaches have been developed to automatically geolocate Twitter users using their tweets. In this paper, a new model to predict home location for Twitter users based on sentiment analysis (Pre-HLSA) is proposed. It predicts the users’ home location using only their tweets, by analyzing some of the tweet’s features. Achieving this goal allows providing geospatial services, especially in the epidemic dispersion. The Pre-HLSA represents user tweets as a set of extracted features and predicts the users’ home locations by analyzing their tweets to find sentiments and polarities, even in the absence of geospatial clues. Then, different classifiers are applied. The experimental results show a promising performance compared to the previous methods in terms of accuracy, mean and median performance measures. It achieves up to 85% accuracy, 223 km mean, and 96 km median.