SRM University-AP is indeed proud of its young and intelligent minds who continue to bring honour and glory to the institution from across the globe. Pulkit Jasti and Tankala Yuvaraj, two of our students from the Department of Computer Science Engineering currently pursuing Semester Abroad Programme at the University of California, Berkeley have won first prize in the prestigious SF Hacks conducted by San Francisco State University, USA, and bagged a total of $950 ($600 for 1st Prize, $250 for Best UI/UX Design, and $100 for Best AIML Hack).

The world has always been ruled and sustained by ideas. Innovating and executing the unthinkable are what helped us tide over the unprecedented hardships the pandemic entailed. SF Hacks 2022, San Francisco’s largest collegiate hackathon was conceived to hatch some striking ideas under the tracks: inclusivity, mental health, sustainability, and machine learning to put the latest technologies to use in the fittest way possible to render solutions to the unending maladies of corona and climate change.

Pulkit Jasti and Tankala Yuvaraj have tread out of the way to introduce an AI-based classroom system that monitors the mental-well being of the students. It is an unfortunate fact that our classrooms have often overlooked the emotional and mental well-being of the students. The transition to virtual mode has made the scenario even worse. Researches state that the depression rates in students between ages 10-18 have increased by 72% since the pandemic.

According to Pulkit and Yuvaraj, this incredible innovation monitors various parameters like facial expressions, voice, attentiveness of a student during the class and generates a meta score that gives an overall idea about the mental well-being of the student. Based on this score, the school counsellors will be notified and then the student can have a one on one therapy session with the counsellor. This system can help identify signs of depression at early stages which makes classroom a safe learning environment for students.

They were determined to come up with an effective solution to redefine the conventional classroom setup and make learning a wholesome experience. “After selecting a problem and drafting the base of the project, we were assured that it could create a positive impact for students during these unprecedented times of the Covid-19 outbreak”, they said.

“During the hackathon, we ran into a lot of technical issues and roadblocks but were able to overcome them and submit our final prototype. To be a part of such a huge event where there were around 1000+ participants from over 26 countries was indeed a remarkable learning experience”, they expressed their feeling of contentment. “We can never thank enough our faculty at SRM for their enormous support throughout our journey at the University of California Berkeley” they added.

Continue reading →

Understanding stock market trends is crucial for investors to make key decisions. It was indeed a wonderful moment when Katla Sai Naveen from the Department of Computer Science and Engineering, presented a paper for the first time with an intelligent solution to that problem. The paper “A Novel Stock Price Prediction Scheme from Twitter Data by using Weighted Sentiment Analysis” was presented at the 12th International Conference on Cloud Computing, Data Science & Engineering (CONFLUENCE-2022), organised by Amity University, Noida, UP, India. It was co-authored by Nikhila Korivi, Godavarthi Chandra Keerthi under the mentorship of Dr V M Manikandan, Assistant Professor, Computer Science and Engineering. The paper will later be published in IEEE Xplore Digital Library.

Abstract:

Stock market forecasting is one of the most interesting research areas for many professionals and researchers. Economic conditions, investor sentiment, current events, future guidance, and a variety of other factors have an impact on the stock market. Since the stock market changes swiftly from time to time, it might be tough for a user or investor to keep up with the shifting trend. Combining sentiment analysis with a machine learning model, a solution to this problem has been introduced. Sentiment analysis is a text mining procedure that has one of the most important uses in analysing user reviews and evaluating the overall sentiment of a piece of text. The purpose of this research work is to create a machine learning model that takes recent tweets from the Twitter API and categorises each message as positive, bad, or neutral. Later, the impact of the person who wrote the tweet is also considered while predicting the trend. The parameters such as the total number of followers, the emotion of each comment on each post of selected stock, the number of likes and retweets are considered. An overview of the selected stock’s potential will be given to the user as the output.

This research will be useful for businessmen and people with enthusiasm for the stock market. The research will provide insights and intelligence to help make profitable decisions. False positives during sentiment analysis is a major concern in this domain. The team is focused on improving the existing approaches with better methods to identify false positives.