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). Since then, I have worked on around 2 projects. One of them was an “Intelligent Investment Research For Value Investors” website, in which I worked as a python developer and ML engineer. As an ML engineer, I developed a news sentiment model.
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) algorithm as the best match for the solution which we were interested in. Also, this algorithm is pretty fast and accurate in sentiment calculation.
Highlighting some features of VADER, this model is used for text sentiment analysis that is sensitive to both polarity (positive/negative) and intensity (strength) of emotion. 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– Words like ‘love,’ ‘enjoy,’ ‘happy,’ ‘like’ all convey a positive sentiment. Also, VADER is intelligent enough to understand the basic context of these words, such as “did not love” as a negative statement. It also understands the emphasis of capitalization and punctuation, such as “ENJOY.”
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.
