Be it indigenous or foreign language, languages are core for communicating messages from one person to another or group of persons. Primarily, it is learnt at home, schools, through the media like television and radio programmes. However, most of these language-teaching approaches do not measure the percentage growth of people who have gained the knowledge of the language over the years; they also lack the capacity to foretell the range of people that will acquire the knowledge of the language in the latest future. This is because several of the language teaching aids do not have the required dataset to describe and effectively predict the state of the language (a category of people who can speak and write the language) now, and against the future. Here, the research proposed an analytic game based model for Yoruba language evaluation. The essence is first to ascertain the user’s initial knowledge of a language, train users through difference fun filled game stages and levels, evaluate the user at the end of every level and analyse the clustered dataset of users game points to describe and predict the state of the language by using a dual level predictive analytics technique.

One natural and successful technique to have retrieved documents that is relevant to users’ intention is by expanding the original query with other words that best capture the goal of users. However, no matter the means implored on the clustered document while expanding the user queries, only a concept driven document clustering technique has better capacity to spawn results with conceptual relevance to the users’ goal. Therefore, this research extends the Concept Based Thesaurus Network document clustering techniques by using the Latent Semantic Analysis tool to identify the Best Fit Concept Based Document Cluster in the network. The Fuzzy Latent Semantic Query Expansion Model process achieved a better precision and recall rate values on experimentation and evaluations when compared with some existing information retrieval approaches.