Multi-Join Query Optimization Using Ant Colony Algorithm and Genetic Algorithm. - 30/09/2023 00:22 EDT

One of the world's most intense sporting rivalries in cricket is between India and Pakistan. Both teams' players are always under tremendous pressure to win the game because it is not just a game but a cultural war between India and Pakistan, more extensive than the finals. Sentiments of people change before and after any game, and to show their sentiments, people use social media platforms like Twitter. In ICC Cricket World Cup 2019: India Vs Pakistan Becomes Most Tweeted ODI Fixture. Tweets about India Vs. Pakistan's cricket match is a valuable medium to analyze how cricket fans’ sentiments change before and after the game. These tweets can be positive, neutral, and negative, which can be detected by sentiment analysis (SA). Many natural language processing models have been proposed to solve the sentiment classification problem [2]. While most models focus on binary sentiment classification, i.e., positive and negative, the Bidirectional Encoder Representation from Transformers (BERT) model stands out as it can classify sentiments of each tweet into multiple categories such as very negative, negative, neutral, positive, and very positive. Hence BERT model is more efficient and can process extensive text data and perform fine-grained

SA on the Twitter data of the ICC Men’s Cricket World Cup -2022 for two countries, India and

Pakistan. This research project aims to extract people's sentiments and opinions using the

BERT model from the Twitter data of the ICC Men’s Cricket World Cup -2022 for two countries, India and Pakistan. The BERT model converts words or text into numbers by leveraging them and using them to train a machine learning (ML) model to predict what the people of both countries think before and after the game. These predictions can be made by different ML and NLP classifiers

Computer Science Machine Learning (ML) NLP Python

Projektin tunnus: #37250880

Tietoa projektista