Buscador interno Web con procesamiento del lenguaje natural y métricas de similitud de inteligencia artificial tomando como caso de estudio un E-commerce

Abstract

Nowadays, Natural Language Processing con- tributes to the advancement of different areas and applications such as voice recognition, web search engines, social mining, etc. This scientific article applies Natural Language Processing techniques for the development of an internal web search engine and recommender system in an e-commerce. The system is deployed in a PaaS with a NoSQL database, and a dataset with 100 documents about literary works. Each document is structured by 15 fields, and for the implementation of the system, only six document fields’ were considered. The behavior of the search engine compares a query with the corpus of documents using the Jaccard coefficient, the Sorensen- Dice coefficient, and the Salton cosine. Also, the recommender system applies similarity metrics to find books similar to the last ones viewed by the user. The tools were validated through functional and non-functional tests. The functional tests used human validation through a satisfaction survey in a group of 25 people between 23 and 25 years old with a university education. The results showed that at least 65% of users rated the tools with the highest level of satisfaction. For the non-functional tests, stress and load tests were carried out, obtaining a high latency in some cases, due to the fact that free services were used.