MahaEmoSen: towards emotion-aware multimodal Marathi sentiment analysis

Abstract

The proliferation of social media platforms in the internet era has led to a exponential growth of user-generated textual and visual content. Microblogs on platforms such as Twitter are extremely useful for comprehending how individuals feel about a specific issue through their posted texts, images, and videos. Given the vast volume of data generated, there is a critical need for methods that can e↵ectively analyze the emotional and sentimental inclination within the content. Individuals express themselves in a variety of languages and, lately, the number of people preferring native languages has been consistently increasing. Marathi language is predominantly spoken in the Indian state of Maharashtra. However, it remains an under-explored domain in sentiment analysis research. In light of the above, we propose an emotion-aware multimodal Marathi sentiment analysis method (MahaEmoSen). Unlike the existing studies, we leverage emotions embedded in tweets besides assimilating the contentbased information from the textual and visual modalities of social media posts to perform a sentiment classification. We mitigate the problem of small training sets by implementing data augmentation techniques. A word-level attention mechanism is applied on the textual modality for contextual inference and filtering out noisy words from tweets. Experimental outcomes on a real-world social media dataset demonstrate that our proposed method outperforms the existing methods for Marathi sentiment analysis notably in resource-constrained environments. Keywords: Marathi, Sentiment analysis, emotions, multimodal data classification.