Prajwal Reddy mentions in his research paper that his analysis is a step ahead of previous research done in this way
Prajwal Reddy claims that his AI model has an accuracy rate of 72.7%. He noted that the results of the AI model could be expanded to help predict elections in other states.
Prajwal Reddy, a Class 11 student, developed an artificial intelligence model to predict election results. The AI model developed by Prajwal uses the Sentiment Polarity Score. While studying at Greenwood High International School, Prajwal Reddy used his AI model to analyze tweets by various politicians in Karnataka. The model focuses on engagement ratings of tweets tweeted by politicians. The model assigns a score based on the tweet’s content, language, number of likes, replies and retweets.
As Prajwal Reddy said, their AI model can be adapted to any state or national election result. Prajwal Reddy mentions in his research paper that his analysis is a step ahead of previous research done in this way. Prajwal says that his model goes further because it also looks at other factors, including the number of retweets, likes and comments. These factors measure the engagement of a tweet tweeted by a politician. Speaking exclusively with News18, Prajwal Reddy said that datasets are important for analyzing sentiment polarity.
Prajwal Reddy claims in his research paper that his AI model is 72.7% accuracy rate. He noted that the AI model’s results could be expanded to help predict elections in other states, and potentially to understand the impact of positive and negative emotions on a political candidate’s ability to win. Can The higher the score, the higher your chances of winning. When asked how bots might affect the outcome of their AI-powered model, he said that bots would reduce the quality of engagement ratings overall.
Sharing the methodology of his AI model, Prajwal Reddy mentioned that, sentiment analysis and polarity is conducted on each tweet for each candidate. The text is translated into English if it is in the local language to successfully perform sentiment analysis. Prajwal Reddy claims that the translation of the tweet body only reduces the information conveyed in the form of the message, not necessarily to convey the pure meaning of the text.
In concluding, Prajwal mentioned that their AI model proves promising for future applications. Thus tweet engagement can be seen to be related to higher chances of winning. They say their analysis can be applied to tweets for the upcoming 2024 general election to predict which politician will win each constituency. A better data collection is the requirement and challenge of his model to make the model successful.
read all latest education news Here