The changing advancements in the current technology of many social blogging sites have brought a drastic change in user-query processing through recommender systems (RS), where the socio-economic platform is using for public recommendation system. A suitable user-query recommender system has become a critical issue for the researchers to attain a proper user-query decision to categorize the user-query sentiment score and to provide compared detail information about the user-query extraction. To provide the user-query recommendation in parallel with the textual user reviews, user ranking through numerical values, user voting and user views made it difficult in predicting the true recommendations. In order to design a true recommendation system from public open data (POD) repository, in this paper, relevant feedback-based user-query log recommender system proposed. In the proposed recommender system, user-query logs based on the decision, score, and extraction made on the query log of user opinion by comparing the categorized user-query logs through attaining system recommendations. The developed recommender system can understand the user-query features through sentiment score feedback mechanism through proposed fuzzy rules and interprets the user-query by classification and representation process. Proposed recommender system experiments performed on Twitter datasets obtained from real-world scenarios, the values of precision, F-measure, and recall have been calculating, and the comparative results discussed, which have shown better than the previously proposed recommendation systems.