Ontology based Semantic Query Expansion for Searching Queries in Programming Domain

Information on the web is growing rapidly; learning programming languages has become one of the most widely searched topics. Programmers and people of several backgrounds are now using Web search engines to acquire programming information, including information about a specific language or topic. Nonetheless, due to a lack of programming knowledge, many laypeople have difficulties in forming appropriate queries to articulate their inquiries, so they used to write short queries, which leads to vocabulary problems and contextless query. Besides, semantics is almost neglected in traditional search query since it is just keyword-based searches, which deem their search to be imprecise with irrelevant results, due to the use of unclear keywords. A Semantic query expansion method is proposed for disambiguating queries in computer programming domain using ontology. The integration of Cosine similarity method into the proposed model improved the expanded query, and accordingly, the searching results. The proposed system has been tested with several ambiguous and misspelled queries and the generated extensions proved to retrieve more relevant results, when applied to a search engine. The quality of the retrieved results for the expanded queries, are much higher than that for the crude queries. The proposed technique was implemented, and then tested with external independent testers. They confirmed the mechanical test results and displayed its improvement with an average of precision @10 82.2% and 91.1% respectively. The results were promising and therefore open further research directions.

@article{Khedr2021,
  title     = {Ontology based Semantic Query Expansion for Searching Queries in Programming Domain},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {12},
  number    = {8},
  year      = {2021},
  publisher = {The Science and Information Organization},
  author    = {Manal Anwer Khedr and Fatma A. El-Licy and Akram Salah},
  doi       = {10.14569/IJACSA.2021.0120852},
  url       = {https://doi.org/10.14569/IJACSA.2021.0120852}
}