A novel method for detecting psychological stress at tweet level using neighborhood tweets

There is an increasing interest in the study of detecting psychological stress from the social media like Twitter. However, Twitter has a limitation on the number of characters used per tweet, resulting in data sparsity. Many techniques were proposed to detect stress at the tweet level, but most of them failed to leverage the text content to reduce the impact of data sparsity. In this work, two solutions are proposed to further leverage the text content for the tweet level stress detection. First, a new feature, Sarcasm_Level, is computed to indicate the sarcasm present in the tweet's content and its influence in detecting stress. Second, a novel neighborhood tweet-based stress detection method is developed, which is a logistic regression-based approach that integrates the content of previous tweets, also known as neighborhood tweets. Experimental results reveal that the proposed model has significantly better performance in detecting stress since it incorporates the information from neighborhood tweets. Also, with the inclusion of the new feature, the proposed model outperformed other well-known machine learning models like support vector machines, random forests and logistic regression with better accuracy and F1score. (c) 2021 The Authors. Published by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Automated summary

There is a growing interest in studying how to detect psychological stress from social media platforms like Twitter. This research addresses the issue of sparse data caused by Twitter's character limitation and proposes two solutions to leverage the text content for stress detection at the tweet level. The first solution introduces a new feature called "Sarcasm_Level" to measure the presence of sarcasm in tweets and its influence on stress detection. The second solution is a novel approach that incorporates the content of previous tweets, known as neighborhood tweets, for stress detection. Experimental results demonstrate that the proposed model outperforms other machine learning models in stress detection by incorporating information from neighborhood tweets and incorporating the new feature.