Hate speech has emerged as a pressing issue on social media platforms, fueled by the increasing availability of multimodal data and easy internet access. Addressing this problem requires collaborative efforts from researchers, policymakers, and online platforms. In this study, we investigate the detection of hate speech in multimodal data, comprising text-embedded images, by employing advanced deep learning models. The main objective is to identify effective strategies for hate speech detection and content moderation. We conducted experiments using four state-of-the-art classifiers: XLM-Roberta-base, BiLSTM, XLNet base cased, and ALBERT, on the CrisisHateMM[4] dataset, consisting of over 4700 text-embedded images related to the Russia-Ukraine conflict. The best findings reveal that XLM-Roberta-base exhibits superior performance, outperforming other classifiers across all evaluation metrics, including an impressive F1 score of 84.62 for sub-task 1 and 69.73 for sub-task 2. The future scope of this study lies in exploring multimodal approaches to enhance hate speech detection accuracy, integrating ethical considerations to address potential biases, promoting fairness, and safeguarding user rights. Additionally, leveraging larger and more diverse datasets will contribute to developing more robust and generalised hate speech detection solutions.

Depression is a prevalent mental illness characterized by feelings of sadness and a lack of interest in daily activities. Early detection of depression is crucial to prevent severe consequences, making it essential to observe and treat the condition at its onset. At ACL-2022, the DepSign-LT-EDI project aimed to identify signs of depression in individuals based on their social media posts, where people often share their emotions and feelings. Using social media postings in English, the system categorized depression signs into three labels: “not depressed,” “moderately depressed,” and “severely depressed.” To achieve this, our team has applied MentalRoBERTa, a model trained on big data of mental health. The test results indicated a macro F1-score of 0.439, ranking the fourth in the shared task.

Due to the intercultural demographic of online users, code-mixed language is often used by them to express themselves on social media. Language support to such users is based on the ability of a system to identify the constituent languages of the code-mixed language. Therefore, the process of language identification that helps in determining the language of individual textual entities from a code-mixed corpus is a current and relevant classification problem. Code-mixed texts are difficult to interpret and analyze from an algorithmic perspective. However, highly complex transformer- based techniques can be used to analyze and identify distinct languages of words in code-mixed texts. Kannada is one of the Dravidian languages which is spoken and written in Karnataka, India. This study aims to identify the language of individual words of texts from a corpus of code-mixed Kannada-English texts using transformer-based techniques. The proposed Distilka model was developed by fine-tuning the DistilBERT model using the code-mixed corpus. This model performed best on the official test dataset with a macro-averaged F1-score of 0.62 and weighted precision score of 0.86. The proposed solution ranked first in the shared task.