Information retrieval experiment on subjective words query expansion

For information retrieval systems, the quality of searching is most important. There are many techniques to improve the quality of search, the query expansion (QE) is considered in order to improve the search result in terms of recall and user satisfaction. This paper proposed the query expansion technique using keyword-based query. These semantic terms are added to the original query in order to reformulate query before sending to the searching process. The experiments were tested on twitter data collection which class is annotated by human. The results show that the retrieval effectiveness is considerably higher than using only original query. Compared to the base-line system, this method provides higher performance in terms of recall and precision.