An Automated Learning System for Twitter Trends

Twitter is the social media platform for real-time broadcasting of information on world events. The microblogging site contains and continues to generate huge amounts of data along with the growing breadth of a geographically diverse user base. Qualitative analysis of this enormous data will require substantial effort on information filtering to successfully drill down to relevant topics and events. This paper presents an automated learning system for trends in twitter to generate a recommendation system for users to understand the contexts in a particular trend. We have devised a framework using Apriori Algorithm and Named Entity Recognition on learned twitter trends. The paper also presents schemes for visual representation of the results using concept hierarchies.