Emoji, Sentiment and Emotion Aided Cyberbullying Detection in Hinglish

Aim:

       Cyber bulling is described as the serious, intentional, and repetitive acts of a person’s cruelty toward others using various digital technologies. It is mainly expressed through nasty tweets, texts, or other social media posts. So we analyzing sentiment, emoji and bully detection to control cyber bulling.

 Abstract:

      The advent of the Internet is a boon to society. However, many of its banes cannot be undermined, cyberbullying being one of them. The emotional state and sentiment of a person have a significant influence on the intended content. The current work is the first attempt in investigating the role of sentiment and emotion information for identifying cyberbullying in the Indian scenario. Moreover, emoji information available with tweet texts can provide better understanding of user intention. The developed dataset consists of both modalities, tweet text, and emoji. In India, the majority of communication on different social media platforms is based on Hindi and English and language switching is a common practice in digital communication. An attention-based multimodal, adversarial multitasking framework is proposed for cyberbully detection (CBD) considering two auxiliary tasks: sentiment analysis (SA) and emotion recognition (ER).

Existing System:

        With the advancement of natural language processing (NLP), many studies on the identification of cyberbullying have been conducted in the English language rather than other languages but it contain mixture of hindi and English language so it can’t able to detect accuracy

Problem Definition:

      We have created a new code-mixed corpus called BullySentEmo of tweets (text + emoji) annotated with bully, sentiment, and emotion labels. For further research work on sentiment and emotion-aware CBD, this dataset will certainly help a lot.

Proposed System:

        Developed a Hindi–English code-mixed text corpus from Twitter for Cyber bullying detection. They proposed based on deep learning architectures that include capsule networks and attained predict accuracy.

 Advantage:

       We observed that there is no work available utilizing sentiment and emotion information for cyberbullying detection from code-mixed text. This motivates us to work in this specific domain. The current work is the first attempt to fill this research gap. Emotion To the best of our knowledge, there is only one publicly available Hindi-English code-mixed corpus for cyberbullying detection.