• Piyush Rai
• Dr. Shobhit Sinha

Sentiment analysis, crucial task of Natural Language Processing (NLP), becomes more tedious in the presence of code-mixed slang, where English blends with internet shorthand, colloquial expressions. Traditional monolingual NLP techniques are often inadequate for handling such irregular and informally structured text. The fundamental purpose of sentiment analysis, which is an important part of natural language processing (NLP), is to find and remove the emotional tone of text data. Sentiment analysis now faces additional difficulties as code-mixed languages, like Hinglish, a combination of Hindi and English, become more comm on. Conventional methods mainly handle monolingual data, which leaves code-mixed scenarios unexplored. A comprehensive approach to sentiment analysis on Hinglish is presented in this research article, which addresses problems such as inconsistent transliteration, a lack of standardized grammar, and the dearth of annotated datasets. We illustrate the potential of our method to efficiently analyze sentiments in code-mixed languages by building a solid dataset and utilizing cutting-edge machine learning and deep learning models. Our results make a substantial contribution to the developing field of multilingual natural language processing. Social media, an omnipresent web-based platform, has become a primary forum for discussion and expression, leading to the evolution of a "pseudo-language" in multilingual regions like India. This new linguistic phenomenon often involves code- mixing, where speakers seamlessly interchange languages within utterances, posing significant challenges for Natural Language Processing (NLP) research. This paper focuses on developing methods for sentiment analysis of such code-mixed social media text, specifically involving Indian languages. Sentiment analysis is a well-established area of natural language processing (NLP), but it is hard to do with Indian language texts that are informal and blend code. This work addresses important issues like inconsistent orthography, non-standard grammar, unpredictable abbreviations, and a lack of annotated resources by presenting a thorough framework for sentiment analysis on slang-rich code-mixed data. In order to capture the linguistic variability typical of code-mixed online communication, we create three new corpora from Twitter and Facebook. In order to achieve sentiment classification, the suggested pipeline combines code-mix complexity analysis, sentence boundary detection, word-level language identification, and part-of-speech tagging. Experiments show that deep learning models perform significantly better than traditional machine learning techniques, especially BiLSTM architectures and transformer-based systems like BERT. The results contribute to the wider development of multilingual and sociolinguistic NLP by demonstrating the efficacy of sophisticated neural models for sentiment processing in highly informal, linguistically hybrid social media text.

"Hybrid Machine Learning Strategies for Sentiment Analysis in Mixed-Language Data", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 12, page no.c559-c567, December-2025, Available :http://www.jetir.org/papers/JETIR2512262.pdf

"Hybrid Machine Learning Strategies for Sentiment Analysis in Mixed-Language Data", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 12, page no. ppc559-c567, December-2025, Available at : http://www.jetir.org/papers/JETIR2512262.pdf