Graduate Research Associate
Computer Science and Engineering
The Ohio State University
Here is how my name is pronounced.
- Implementation of LISP interpreter using Java - Part of coursework. (Code available on request)
- Several Neural Network implementations as part of Neural Networks coursework. (Code available on request)
- As part of the Data Mining coursework in my first semester at OSU, I worked on kNN classifiers, k-means clustering and Decision Tree classifiers. The coding was done in Python and R and used packages like numpy, scipy and matplotlib. It can be accessed here. (Python, matplotlib, numpy, scipy, Weka, R)
- As part of the Computational Linguistics coursework in my first semester I had the opportunity to learn and work on CKY parser implementation, Naive Bayes text classification (Sentiment Analysis), Zipf's law verification for text documents, entropy and its significance and a host of other topics. Some of the implementations can be accessed here. (Python)
- As part of the Speech and Natural Language Processing coursework, I experimented with Sentiment Analysis of IMDb movie reviews using Naive Bayes Classifier and Averaged Perceptron. I also had the opportunity to implement the Viterbi algorithm to perform POS tagging on large datasets which included Twitter and IRC data.
- Carried out a project (group of 4) titled "Feature based classifier for differentiating poetry and prose". I was responsible for the baseline classifier which achieved an F1 score of ~85%. (Python, numpy, scipy, CRFSuite)
- Implemented the EM algorithm on a 1-dimensional dataset using R.
- Carried out a project (group of 3) titled "Public Perception to currently showing movies". I was responsible for the entire design and code. Used TMDb API for fetching movie data and cutting down the number of popular movies based on the popularity index. Then used the Tweepy library to gather tweets with a combination of the words which would be used as a hashtag for the movies. Further, TextBlob API and Naive Bayes Classifier were used to perform Sentiment Analysis. (Python, TextBlob, TMDb API, Tweepy library)
- Carried out a project (group of 4) titled "Efficient Information Retrieval using Crawling, Indexing and Ranking". I was responsible for the crawler module which was used to gather links related to a search query. (Java, JSP)