• Bhavesh Tukaram Jadhav
• Amol Joglekar

Slang is a dynamic component of communication it’s important for creating human-like environment because it reflects emotional tones, cultural nuances, and personal emotions. The goal of this research is to improve chatbot conversational capabilities by addressing the unique problems that social media slang presents. The Thought was to make it possible for the model to understand and provide responses that are consistent with the informal language used in social media interactions. For this we created a dataset which had a wide variety of slangs, phrases and informal language sentences taken from various social media conversations. The language model is trained using this information to make sure it understands slangs and generate a appropriate response that user would be expecting. Evaluation would be based on accuracy of the chatbot's understanding and response generation in presence of slang in a question. For successful integration, humor, sentiment and contextual nuances in slang-infused messages must be deciphered by the chatbot leading to more naturalistic interactions between human beings. The Research explores broader implication for enhancing user engagement and satisfaction in a conversation that is done with a chatbot, and creating a new era of natural and culturally aware human-machine interactions. Besides, it also tackles the technical challenges of incorporating slang into language models.

LLM - mistral 7b Instruct, chatbot, social media slangs, NLP, slangs interaction.

"Enhancing the capability of chatbots in interpreting social media slangs and generating appropriate response", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 3, page no.b243-b249, March-2024, Available :http://www.jetir.org/papers/JETIR2403127.pdf

"Enhancing the capability of chatbots in interpreting social media slangs and generating appropriate response", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 3, page no. ppb243-b249, March-2024, Available at : http://www.jetir.org/papers/JETIR2403127.pdf