This project is an aim to create a model for companies and organizations that can deliver better experiences to their customers across the world on the basis of thoughts, beliefs, and mindset of customers themselves through their tweets tweeted on the world-famous microblogging platform Twitter which entertains around 6000 tweets per second. Opinion of people matters a lot to analyze how the propagation of information impacts the lives in a large-scale network like Twitter. Sentiment Analysis of the tweets decides the polarity and inclination of a vast population towards a specific topic, item. person or entity. The ultimate goal is to analyze twitter data to perform algorithms and predict better results through Machine Learning models to evaluate a company or brand in real-time on the basis of the past datasets as well as live data streaming and for changes in their business models, detect anomalies with alert and for enforcing public engagement.
The above graphs illustrate the output of the project. The first graph here shows the tweets being classified in three norms:- positive, negative or neutral. The company here we tracked is ‘APPLE’. And, the time zone which we tracked is UTC. The values show in the next graph are +1 for positive, 0 for neutral and -1 for negative. This graph is a very interactive way to analyze the data and it shows the real-time activity of each time a tweet is captured.
1] A. Go, R. Bhayani, and L. Huang, “Twitter Sentiment Classification using Distant Supervision,” Stanford.edu. [Online]. Available: https://cs.stanford.edu/people/alecmgo/papers/TwitterDistantSupervision09.pdf. [Accessed: 17-Mar-2021].
2] L. Jiang, M. Yu, M. Zhou, X. Liu, and T. Zhao, “Target-dependent twitter sentiment classification,” Aclweb.org. [Online]. Available: https://www.aclweb.org/anthology/P11-1016.pdf. [Accessed: 17-Mar-2021].
3] I. G. Councill, R. Mc Donald, L. V. Google, and 76 Ninth Avenue, “What’s great and what’s not: Learning to classify the scope of negation for improved sentiment analysis,” Googleusercontent.com. [Online]. Available: http://static.googleusercontent.com/media/research.google.com/en//pubs/archive/36744.pdf. [Accessed: 17-Mar-2021].
4] “Twitter Sentiment Analysis using Python - GeeksforGeeks,” Geeksforgeeks.org, 24-Jan-2017. [Online]. Available: https://www.geeksforgeeks.org/twitter-sentiment-analysis-using-python/. [Accessed: 17-Mar-2021].
5] “For Academics - Sentiment140 - A Twitter Sentiment Analysis Tool,” Sentiment140.com. [Online]. Available: http://help.sentiment140.com/for-students. [Accessed: 17-Mar-2021].