Paper Title
SAMBT: Semantically Aware Micro-Blog Tag Recommender Encompassing Bi-Classification Model

Abstract
Microblogs, which are popular among users and have a lot of potential for public engagement, are one of the emerging mediums for short and frequent content accumulation. A semantically aware Micro-Blog Tag Recommender with Bi- Classification Model is proposed in this paper. The proposed SAMBT takes user query as input which is pre-processed, and the metadata is generated and classified. A microblog dataset is classified at the same time, and semantic similarity is calculated to rearrange, rank, and recommend microblogs. The accomplished false discovery rate value is 0.05 compared to the baseline models and yielded the highest precision, recall and accuracy. Keywords - Micro-Blog Tag Recommendation, XG Boost Classifier, Semantic similarity, NMPI Measure, Jaccard Similarity, Charged System Search