With each passing minute, online data is growing exponentially. A bulk of such data is generated from short text social media platforms such as Twitter. Such platforms are fundamental in social media knowledge-based applications like recommender systems. Twitter, for example, provides rich real-time streaming information. Extracting knowledge from such short texts without automated support is not feasible due to Twitter's platform streaming nature. Therefore, an automated method for comprehending patterns in such text is a need for many knowledge systems. This paper provides solutions to generate topics from Twitter data. We present several techniques related to topical modelling to identify topics of interest in short texts. Topic modelling is inherently problematic in shorter texts with very sparse vocabulary in addition to the informal language used in their dissemination. Such findings are informative in knowledge extraction for social media-based recommender systems as well as in understanding tweeters over time.