- Akshaya Ramaswamy (AXR170131)
- Aswin Krishna Gunasekaran (AXK175831)
- Sai Spandan Gogineni (SXG175130)
- Sankalp Rath (SXR173830)
- Sivagurunanthan Velayutham (SXV176330)
- Gather tweets using twitter search API, pre-process tweets and extract important features to build a model using spark MLlib.
- Stream tweets using twitter streaming API and push data into kafka topic using a kafka producer after applying partial filters.
- Read from kafka topic using kafka consumer.
- Perform tokenization, stopword removal etc. to pre-process the data.
- Extract machine readable features using bag of words approach and predict instances with the model.
- Tweets are indexed to elasticsearch after classification Constructed a traffic heat map by reading the coordinates data from elasticsearch.
- TWEEPY
- KAFKA
- ELASTICSEARCH
- GOOGLE MAP’S API
- SPARK STREAMING
- SPARK MLIB
- NLTK
