Harshita Sharma's repositories
lecture-notes
Lecture-notes and question papers for courses taken @IIIT-H. Assignments and projects (if available) can be found as separate repositories.
sexism-in-movies
Automating the study of sexism in movies (scripts) using Machine Learning and NLP.
air-pollution-in-delhi
Analysis and prediction of air pollutant concentration and AQI using Prophet and SARIMAX
AQI-and-effect-of-lockdown
Predict the AQI of Indian cities using ML after lockdown using data from 2015-2020; data visualisation for different cities for different periods of time.
ellipsis-detection
A rule-based NLP Project to detect licensor and antecedent of nominal ellipsis in a sentence.
elm-programming
Projects built in elm
Feature-Extraction-OpenSMILE-pathological-dataset-II
Extracted ComParE features using OpenSMILE tool and MFCC features from scratch from the pathological dataset 2 and performed classification using both features and compared them.
Angular-FireBase
Demo-Lists
Assignment-1
Template for Assignment 1
genquest
Automatic question generation by using NLP
Bayesian-Network
Bayes-Net modelled on a given problem with a query example.
Chillar
A mobile-money app in python.
clean-the-code
Cleaning the code @unclebob
cytoscape.js-blog
The Cytoscape.js blog, using Github pages and Jekyll
Extreme-Tic-Tac-Toe
An AI bot that plays a 3*3*3*6 extension of Ultimate Tic-Tac-Toe.
hellomasaya.github.io
Personal Web Page
linguistics-data
Assignments covered as part of the course - Linguistics Data: Collection and Modeling
Linux-C-Shell
A mini shell which supports all basic Linux commands. It also supports background processes, signal handling along with avoiding Zombie Processes.
Mario-game
A UNIX terminal game based on original SuperMario. The game is developed purely in python.
markdown-cheatsheet
Markdown Cheatsheet for Github Readme.md
Sentiment-Analysis-On-Hindi-Reviews
We have used 250 sentences of movie reviews available for research from IIT bombay and also crawled and manually annotated 750 reviews from jagran.com, In total 1000 reviews. After preprocessing the dataset, We generate the featureset as a vector-based approach using Term frequency, tfidf for unigrams and bigrams. Then we used three approaches to predict the sentiment of a review. Approaches used are Resource based, In-language semantic analysis and Machine Translation based semantic analysis.
verb-cat-for-hindi-wps
Verb Categorisation for Hindi Word Problem Solving
voiced-unvoiced-classification-using-zff
A Speech Technology project to classify voices and unvoiced regions in a speech signal using zero frequency filter
Web-Scraping
Scraped the list of all the bestseller books available on amazon.in and amazon.com.
WebGL-3D
A 3D game like Subway Surfer created using WebGL with shader tasks like grayscale, texture and lighting.
word-alignment-models
IBM model 1