A Re-classification of Information Seeking Tasks and Their Computational Solutions

TL;DR

This paper introduces a new taxonomy for information seeking tasks based on search iterations, goals, and procedures, and reviews machine learning solutions aligned with these categories.

Contribution

It proposes a novel re-classification framework for IS tasks and analyzes corresponding machine learning solutions and evaluation campaigns.

Findings

New taxonomy with dimensions: search iterations, goal types, procedures

Matching machine learning solutions to each new category

Overview of evaluation campaigns for IS systems

Abstract

This article presents a re-classification of information seeking (IS) tasks, concepts, and algorithms. The proposed taxonomy provides new dimensions to look into information seeking tasks and methods. The new dimensions include the number of search iterations, search goal types, and procedures to reach these goals. Differences along these dimensions for the information seeking tasks call for suitable computational solutions. The article then reviews machine learning solutions that match each new category. The paper ends with a review of evaluation campaigns for IS systems.