RESEARCH ON THE TECHNIQUE OF SENTIMENT ANALYSIS WITH SARCASM DETECTION IN MULTILINGUAL DATA

The majority of our time is now spent on social media platforms like Facebook, Twitter, Instagram, WhatsApp, Snapchat, and many more. They are filled with a variety of ideas and viewpoints expressed as user information gathered through browsing analytics. Now we're discussing those that are often utilized in Twitter debates. It has become one of the most important tools for researching various emotions utilising the same database and thought analysis algorithms since tweets allow users to express their ideas and feelings to others. There are three distinct categories of tweets: good, bad, and ugly. In statistics, good data is represented by positive data, bad data by negative data, and no data by neutral data. A method for determining user sentiment and categorising it as either positive, negative, or neutral is sentiment analysis. Data mining is a crucial technique for gathering facts and examining viewpoints on social media platforms. To categorise tweets as excellent, terrible, or neutral, combine data mining techniques with additional techniques including text mining, natural language processing, and artificial intelligence. This project's primary goal is to understand the motivations behind the tweets. For convenience of data analysis, the model converts information from various tweets that are accessible in English, Hindi, French, German, etc. into one language, English. The model also recognises sarcasm since there are so many sarcastic tweets in the file. A suggested methodology that enhances cascade outcomes in emotional evaluation using machine learning. For this, a range of machine learning techniques and their combinations have been used to evaluate the recommended model. and the results have demonstrated that it performs better as a standalone classifier.