Fusing location and text features for sentiment classification

TL;DR

This paper introduces a method that combines geo-location features with text data to improve sentiment classification of tweets using CNN and LSTM models, demonstrating enhanced accuracy over text-only approaches.

Contribution

The study proposes a novel approach of integrating geo-location features with text data for sentiment analysis, showing improved performance in classifying geo-tagged tweets.

Findings

Geo-location features improve sentiment classification accuracy.

Concatenating location data with text enhances tweet representation.

The method outperforms text-only models in experiments.

Abstract

Geo-tagged Twitter data has been used recently to infer insights on the human aspects of social media. Insights related to demographics, spatial distribution of cultural activities, space-time travel trajectories for humans as well as happiness has been mined from geo-tagged twitter data in recent studies. To date, not much study has been done on the impact of the geolocation features of a Tweet on its sentiment. This observation has inspired us to propose the usage of geo-location features as a method to perform sentiment classification. In this method, the sentiment classification of geo-tagged tweets is performed by concatenating geo-location features and one-hot encoded word vectors as inputs for convolutional neural networks (CNN) and long short-term memory (LSTM) networks. The addition of language-independent features in the form of geo-location features has helped to enrich the tweet representation in order to combat the sparse nature of short tweet message. The results achieved has demonstrated that concatenating geo-location features to one-hot encoded word vectors can achieve higher accuracy as compared to the usage of word vectors alone for the purpose of sentiment classification.