Stress detection using natural language processing and machine learning over social interactions

Abstract

Cyberspace is a vast soapbox for people to post anything that they witness in their day-to-day lives. Social media content is mostly used for review, opinion, influence, or sentiment analysis. In this paper, we aim to extend sentiment and emotion analysis for detecting the stress of an individual based on the posts and comments shared by him/her on social networking platforms. We leverage large-scale datasets with tweets to accomplish sentiment analysis with the aid of machine learning algorithms and a deep learning model, BERT for sentiment classification. We also adopted Latent Dirichlet Allocation which is an unsupervised machine learning method for scanning a group of documents, recognizing the word and phrase patterns within them, and gathering word groups and alike expressions that most precisely illustrate a set of documents. This helps us to predict which topic is linked to the textual data. With the aid of these models, we will be able to detect the emotion of users online. Further, these emotions can be used to analyze stress or depression. In conclusion, the ML models and a BERT model have a very good detection rate. This research is useful for the well-being of one's mental health. The results are evaluated using various metrics at the macro and micro levels and indicate that the trained model detects the status of emotions based on social interactions.

Volleyball Sports Teaching Based on Augmented Reality and Wireless Communication Assistance

“…In addition, the IRS controller can communicate and coordinate with other network components (such as BS) through a separate feedback link, enabling low-rate information exchange. Figure 5 also shows an example of the structure of reflectors, each controlled by a switching diode [ 19 ]. By controlling the bias voltage through the DC feeder, the switching diode can be switched between “on” and “off” states, resulting in a phase difference of π .…”

Anime clustering for automatic classification and configuration of demographics

“…Therefore, according to LDA's logic, a textual document is composed of a distribution of such topics (Blei et al, 2003). The operation of LDA consists of creating a distribution of textual documents by topic, and a separate distribution of words by topic (Nijhawan et al, 2022).…”

“…Parameters α and η are parameters of Direchlet distributions. Parameter α controls the distribution of documents per topic and parameter η, the distribution of words per topic (Nijhawan et al, 2022). These parameters can be modified to obtain topics with more or fewer keywords, and documents composed of more or fewer topics.…”

Aspect-based Sentiment Analysis for Bengali Text using Bidirectional Encoder Representations from Transformers (BERT)

“…They had an F1-score of 84.3% for offensive language detection, 81.8% for hate speech detection, and 45.1% for fine-grained hate-speech recognition by applying BERT. BERT was used by Nijhawan et al for sentiment classification in their research [8]. Experiments revealed that, despite its comparatively simpler structure, the BERT model outperforms many prominent models in this subject.…”