• Shubham Das
• Dr. Tanya Singh

The popularity of sentiment analysis in social media content has grown over the past several years as a result of its many applications in research on human-computer interaction, consumer behaviour, psychology, smart systems, etc. This problem has received a lot of focus due to the enormous amounts of data that are accessible via social media, which is frequently utilised to express thoughts and ideas. This study will use a labelled Hinglish dataset to pinpoint emotions. By using transformer-based models and multilingual word embeddings produced from FastText approaches, deep learning-based techniques are used to recognise emotions in tweets with mixed Hindi-English coding. Many deep learning models have been used to assess attitudes, including convolutional neural networks (CNN), long short-term memory (LSTM), bi-directional long short term memory (Bi-LSTM), and other transformer models like BERT. Convolutional neural networks (CNN) outperformed other models in terms of accuracy, coming in at 75.25%.

NLP, FastText, convolutional neural networks (CNN), long short term memory (LSTM), and bi-directional long short term memory (Bi-LSTM), Bidirectional Encoder Representations from Transformers BERT

"Sentiment Recognition of Hinglish Code Mixed Data using Deep Learning Models based Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 11, page no.f661-f664, November-2022, Available :http://www.jetir.org/papers/JETIR2211585.pdf

"Sentiment Recognition of Hinglish Code Mixed Data using Deep Learning Models based Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 11, page no. ppf661-f664, November-2022, Available at : http://www.jetir.org/papers/JETIR2211585.pdf