{"id":59763,"date":"2022-02-18T08:21:30","date_gmt":"2022-02-18T02:51:30","guid":{"rendered":"https:\/\/www.mygreatlearning.com\/blog\/a-great-opportunity-to-explore-and-implement-concepts\/"},"modified":"2025-01-20T20:57:56","modified_gmt":"2025-01-20T15:27:56","slug":"a-great-opportunity-to-explore-and-implement-concepts","status":"publish","type":"post","link":"https:\/\/www.mygreatlearning.com\/blog\/a-great-opportunity-to-explore-and-implement-concepts\/","title":{"rendered":"A great opportunity to explore and implement concepts - Omkar Sahasrabudhe, PGP AIML"},"content":{"rendered":"\n

Hi, I am Omkar Sahasrabudhe with 3+ years of experience. I work at Excellarate as a Machine Learning Engineer. I was promoted to a Machine Learning Engineer at the end of the course (PGP in AIML<\/a>). Since then, I have worked on around 2 projects. One of them was an \u201cIntelligent Investment Research For Value Investors\u201d website, in which I worked as a python developer and ML engineer. As an ML engineer, I developed a news sentiment model. <\/strong><\/p>\n\n\n\n

Finding the right data sets is crucial for those looking to advance their analytics or data science projects. I recommend checking out our blog, \"Free Data Sets for Analytics\/Data Science Project.<\/a>\"<\/strong> It's a valuable resource for discovering high-quality, free data sets to help you drive your projects forward and enhance your skills.<\/p>\n\n\n\n

As a part of problem analysis, we considered different text classification techniques. And at the end, we found the VADER ( Valence Aware Dictionary for Sentiment Reasoning)<\/strong> algorithm as the best match for the solution which we were interested in. Also, this algorithm is pretty fast and accurate in sentiment calculation. <\/p>\n\n\n\n

Highlighting some features of VADER<\/strong>, this model is used for text sentiment analysis that is sensitive to both polarity (positive\/negative) and intensity (strength) of emotion.<\/strong> It relies on a dictionary that maps lexical features to emotion intensities known as sentiment scores. The sentiment score of a text can be obtained by summing up the intensity of each word in the text. For example<\/strong>- Words like \u2018love,\u2019 \u2018enjoy,\u2019 \u2018happy,\u2019 \u2018like\u2019 all convey a positive sentiment. Also, VADER is intelligent enough to understand the basic context of these words, such as \u201cdid not love\u201d as a negative statement. It also understands the emphasis of capitalization and punctuation, such as \u201cENJOY.\u201d<\/p>\n\n\n\n

This was a great opportunity to explore and implement text classification techniques for sentiment analysis. It was my first production-level ML model. This product has been in the market for more than 8-9 months. And for sure, it is making a great impact in the industry. This model predicts stock sentiment against market sentiment. And it is helping investors with decision-making.<\/p>\n\n\n\n

You can also check out Great Learning in-depth analysis on Tapping Twitter Sentiments during the 2015 Chennai Floods<\/a>. Discover how Twitter data was used to understand public sentiment!<\/p>\n\n\n\n

Must Read<\/h2>\n\n\n\n