A hybrid BERT-CPSO model for multi-class depression detection using pure hindi and hinglish multimodal data on social media

Abstract

Due to the psychological strain that depression causes, there has been a noticeable increase in the number of persons compromising their lives in recent years. Social media platforms provide researchers with an entirely novel viewpoint on identifying individuals who are depressed. Previous research on automatic learning models for depression detection revealed low detection accuracy and an absence of optimizing techniques that could enhance detection accuracy. Furthermore, there is no such dataset, and very little study has been done on the multimodal pure Hindi and code-mixed Hinglish language domains. In light of this, we developed a Hindi dataset and suggested reliable methods for depression detection based on multimodal data, i.e., text and images, using the Hindi and Hinglish languages. This study aims to accomplish three things: first, it will evaluate text data using an effective Bidirectional Encoder Representations from Transformers (BERT) approach and compare it with other transfer learning variants; second, it will analyze image data by suggesting a Convolutional Neural Network (CNN) optimized with a nature-inspired algorithm, namely Particle Swarm Optimization (PSO), or CPSO; and third, it will classify the multimodal data into depressive and non-depressive posts by suggesting a hybrid of the best-performing models on text and images, namely BERT-CPSO (BTCPSO). The results produced with the BERT model showed the best accuracy of 95% for text data, in contrast to RoBERTa, DistilBERT, and XLNet. Further, CPSO outperforms other Machine Learning (ML) and Deep Learning (DL) algorithms for image data with an accuracy of 95%. Additionally, comparing the proposed CPSO with a basic CNN revealed that integrating the PSO technique with CNN increased the model's accuracy in detecting depressed posts by 5%. In conclusion, hybrid BERT-CPSO outperforms other BERT combinations with ML and DL algorithms for multimodal data, achieving 97%, 95%, 98%, and 96%, respectively, in accuracy, recall, precision, and F1-scores. As a result, the findings of comparing the suggested technique with the earlier models show the effectiveness of the approach that has been provided and can help medical professionals diagnose depression with precision.