Sentiment Analysis in Geo Social Streams by using Machine Learning Techniques

Abstract

Massive amounts of sentiment rich data are generated on social media in the form of Tweets, status updates, blog post, reviews, etc. Different people and organizations are using these user generated content for decision making. Symbolic techniques or Knowledge base approaches and Machine learning techniques are two main techniques used for analysis sentiments from text. The rapid increase in the volume of sentiment rich data on the web has resulted in an increased interaction among researchers regarding sentiment analysis and opinion (Kaushik & Mishra, 2014). However, limited research has been conducted considering location as another dimension along with the sentiment rich data. In this work, we analyze the sentiments of Geotweets, tweets containing latitude and longitude coordinates, and visualize the results in the form of a map in real time. We collect tweets from Twitter using its Streaming API, filtered by English language and location (bounding box). For those tweets which don’t have geographic coordinates, we geocode them using geocoder from GeoPy. Textblob, an open source library in python was used to calculate the sentiments of Geotweets. Map visualization was implemented using Leaflet. Plugins for clusters, heat maps and real-time have been used in this visualization. The visualization gives an insight of location sentiments.