TIMME: Twitter Ideology-detection via Multi-task Multi-relational Embedding (code & data)

Node Embeddings in Dynamic Graphs

Collect and process real time twitter data plotting various metrics like volume , proportion, sentiment. Analyze tweet node networks and map them geographically.

Temporal Walk Based Centrality Metric for Graph Streams

A gathering of digital methods recipes for research, teaching and collaborations from across the Public Data Lab.

Build a classifier to classify anti-national tweets from normal tweets based on the Khalistan movement.

twitter scrapper to scarpe the tweets of a particular word and save them in a csv file

Finding similarity index of a community in the twitter network using multiple views through inter-graph random walk kernel (IRWK).

🔍 This project is about searching the twitter for Soccer Prediction using popular keywords and applying sentiment analysis on the data.

Codes and data necessary to reproduce the results of the article K. Shyrokykh, M. Girnyk and L. Dellmuth, "Short Text Classification with Machine Learning in the Social Sciences: The Case of Climate Change on Twitter," submitted.

Utility python package for RG17 and UO17 Twitter tennis data sets.

In this project, I have explored the world of tweet analysis in the case of two European universities: University of Tartu and Lund University.

Twitter Sentiment Analysis

A repository with Twitter data and tweet classifiers using several machine learning approaches to measure the accuracy and performance of the approaches on classifying tweets.🐧

Analysing Twitter data to identify urban issues

A Bidirectional LSTM model to classify whether a given tweet talks about a real disaster or not. This was my project in "CSC 522: Automated Learning and Data Analysis" course at NC State University.

Twitter Semantic Data Mining for Harvey Hurricane Credible Event Detection

Under the broad research question: What are the impact of COVID-19 in ones life? Our team collected Twitter data to answer research hypothesis, producing models, and have a better understanding of the factors that influence one's reaction to the global pandemic.

R code, markdown document, and Gephi files used to create a social network analysis project examining three information operations removed from Twitter in 2021.