Collaborating personalized recommender system and content-based recommender system using TextCorpus

Recommender systems aim to get the relevant data, based on the user's interests. One of the key problems of the recommender systems is to maintain the dataset and to retrieve the data, which is relevant to the user. A common solution is to track the user's preferences and showing the relevant results, however, it is a complex task in terms of time and space. The user data need to be analyzed and learnt using efficient algorithms. To address this problem, we have proposed a method to format the data in the dataset using POS-taggers using NLTK framework. In this paper, we have proposed a user-profile model which uses this tagging mechanism to provide better recommendations compared to the existing state-of-the-art recommender techniques.