What makes a query difficult?

Abstract

This work tries to answer the question of what makes a query difficult. It addresses a novel model that captures the main components of a topic and the relationship between those components and topic difficulty. The three components of a topic are the textual expression describing the information need (the query or queries), the set of documents relevant to the topic (the Qrels), and the entire collection of documents. We show experimentally that topic difficulty strongly depends on the distances between these components. In the absence of knowledge about one of the model components, the model is still useful by approximating the missing component based on the other components. We demonstrate the applicability of the difficulty model for several uses such as predicting query difficulty, predicting the number of topic aspects expected to be covered by the search results, and analyzing the findability of a specific domain.

A Performance Prediction Approach to Enhance Collaborative Filtering Performance

“…The correlation by the Spearman and Kendall functions yields similar results. While being indicative of a positive trend, and not far from previous results in query performance [5], observed correlation values still leave room for further elaboration and refinements of the proposed predictor and alternative ones, as well as the NG metric itself, in order to match the best findings in query performance [7]. The second experiment consists of measuring final performance improvements when dynamic weights are introduced in a user-based CF.…”

“…The prediction methods documented in the literature use a variety of available data as a basis for prediction, such as a query, its properties with respect to the retrieval space [7], the output of the retrieval system [5], or the output of other systems [3]. According to whether or not the retrieval results are used in the prediction, the methods can be classified into pre-and post-retrieval approaches [10].…”

Using a Medical Thesaurus to Predict Query Difficulty

“…[7]) or with the average performance of several models (e.g. [2]). In this study, we use the latter.…”

Query Performance Prediction for Information Retrieval Based on Covering Topic Score

“…Carmel et al [15] attempted to answer the question of what makes a query difficult and discussed the problem thoroughly. They found that the distance measured by the Jensen-Shannon divergence between the retrieved document set and the collection significantly correlated with average precision.…”