ConSTR: A Contextual Search Term Recommender

TL;DR

ConSTR is a new search term recommender that uses user interaction context to improve literature search, featuring a two-layered interface for real-time and historical search term suggestions, demonstrated on arXiv data.

Contribution

It introduces a novel contextual search term recommender with a two-layered interface leveraging user interaction history and current search context.

Findings

Effective in suggesting relevant search terms based on context

Integrated with arXiv's extensive document repository

Enhances literature retrieval experience

Abstract

In this demo paper, we present ConSTR, a novel Contextual Search Term Recommender that utilises the user's interaction context for search term recommendation and literature retrieval. ConSTR integrates a two-layered recommendation interface: the first layer suggests terms with respect to a user's current search term, and the second layer suggests terms based on the users' previous search activities (interaction context). For the demonstration, ConSTR is built on the arXiv, an academic repository consisting of 1.8 million documents.