Deakin University
Browse

File(s) under permanent embargo

Relevance-driven clustering for visual information retrieval on twitter

conference contribution
posted on 2019-01-01, 00:00 authored by Mohamed Reda BouadjenekMohamed Reda Bouadjenek, S Sanner
© 2019 Copyright held by the owner/author(s). Geo-temporal visualization of Twitter search results is a challenging task since the simultaneous display of all matching tweets would result in a saturated display. In such settings, clustering search results can assist users to scan only a few coherent groups of related tweets rather than many individual tweets. However, in practice, the use of unsupervised clustering methods such as k-means does not necessarily guarantee that the clusters themselves are relevant. Therefore, we develop a novel method of relevance-driven clustering for visual information retrieval to supply users with highly relevant clusters representing different information perspectives of their queries. We specifically propose a Visual Twitter Information Retrieval (Viz-TIR) tool which based on a fast greedy algorithm that optimizes an approximation of an expected F1-Score metric to generate these clusters. We demonstrate its effectiveness w.r.t. k-means and a baseline method that shows all top matching results on a scenario related to searching natural disasters in US-based Twitter data. Our demo shows that Viz-TIR is easy to use and more precise in extracting geo-temporally coherent clusters given search queries in comparison to k-means, thus aiding the user in visually searching and browsing social network content. Overall, we believe this work enables new opportunities for the synthesis of information retrieval as well as combined relevance and display-aware optimization techniques to support query-adaptive visual information exploration interfaces.

History

Pagination

349-353

Location

Glasgow, Scotland

Start date

2019-03-10

End date

2019-03-14

ISBN-13

9781450360258

Language

eng

Publication classification

E1.1 Full written paper - refereed

Title of proceedings

CHIIR 2019 - Proceedings of the 2019 Conference on Human Information Interaction and Retrieval

Event

Human Information Interaction and Retrieval. Conference (2019 : Glasgow, Scotland)

Publisher

ACM

Place of publication

New York, N.Y.

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC