Optimized Prediction of Hard Keyword Queries Over Databases

Abstract

Keyword Query Interface on databases gives easy access to data, but undergo from low ranking quality, i.e., low precision and/or recall. It would be constructive to recognize queries that are likely to have low ranking quality to improve the user satisfaction. For example, the system may suggest to the user alternative queries for such difficult queries. Goal of this paper is to predict the characteristics of hard queries and propose a novel framework to measure the degree of difficulty for a keyword query over a database, allowing for both the structure and the content of the database and the results of query. There are query difficulty prediction model but results indicate that even with structured data, finding the desired answers to keyword queries is still a hard task. Further, we will use linguistic features Such as morphological features, syntactical features, and semantic features for effective prediction of difficult keyword queries over database. Due to this, Time required for predicting the difficult keywords over large dataset is minimized and process becomes robust and accurate.
DOI: 10.17762/ijritcc2321-8169.150789