Tweet-Extraction-And-Summarization

IRE Major Project for Tweet Extraction and Summarization

Problem Statement

Given a set of hashtags, scrape twitter for tweets related to them and analyse (summarisation, sentimentanalysis etc.) the scraped content.

Link to Google Drive Here

Directory Structure

├── dataset
│   ├── data.pkl
│   ├── raw-dataset.zip
│   └── stats.txt
├── FinalPresentation.pdf
├── ProjectReport.pdf
├── Project_Scope_Document.pdf
├── README.md
├── ref-papers
│   └── paper1.pdf
└── scripts
    ├── imports.py
    ├── model_load.py
    ├── page_rank.py
    ├── preprocessing.py
    ├── requirements.txt
    ├── sentiment_analysis.py
    ├── training.txt
    ├── twitter_tracker.py
    └── util.py

Running the Code

1. Download the glove pretrained embeddings
2. Extract the zip of Dataset
3. Run the scripts.

Contributers:

1. Chaitanya Agarwal
2. Tanvi Kamble
3. Apurvi Mansinghka
4. Jyoti Gambhir