Repository logoCyprus University of Technology
Log In(current)
Ελληνικά
English
  1. Home
  2. Cyprus University of Technology (Research Output)
  3. Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation
  4. Identifying image tags from Instagram hashtags using the HITS algorithm
  • Details

Identifying image tags from Instagram hashtags using the HITS algorithm

Date Issued
March 29, 2018
Author(s)
Giannoulakis, Stamatios  
Tsapatsoulis, Nicolas  
Ntalianis, Klimis S.  
DOI
10.1109/DASC-PICom-DataCom-CyberSciTec.2017.29
Abstract
Many automatic image annotation methods are based on the learning by example paradigm. Image tagging, through manual image inspection, is the first step towards this end. However, manual image annotation, even for creating the training sets, is time-consuming, complicated and contains human subjectivity errors. Thus, alternative ways for automatically creating training examples, i.e., pairs of images and tags, are crucial. As we showed in one of our previous studies, tags accompanying photos in social media and especially the Instagram hashtags can be used for image annotation. However, it turned out that only a 20% of the Instagram hashtags are actually relevant to the content of the image they accompany. Identifying those hashtags through crowdsourcing is a plausible solution. In this work, we investigate the effectiveness of the HITS algorithm for identifying the right tags in a crowdsourced image tagging scenario. For this purpose, we create a bipartite graph in which the first type of nodes corresponds to the annotators and the second type to the tags they select, among the hashtags, to annotate a particular Instagram image. From the results, we conclude that the authority value of the HITS algorithm provides an accurate estimation of the appropriateness of each Instagram hashtag to be used as a tag for the image it accompanies while the hub value can be used to filter out the dishonest annotators.
Funding(s)
Network for sOcial compuTing REsearch (NOTRE)  
Subjects

Bipartite network

Graphs

Hashtags

HITS algorithm

Image retrieval

Image tagging

Instagram

Machine learning

Explore by
  • Collections
  • Research Outputs
  • Researchers
  • Faculty & Departments
  • Theses
  • Patents
  • Projects
  • Journals
  • Conferences
Useful Links
  • Researcher Portfolio Guide
  • Researcher Profile
  • Create an ORCID ID
  • CUT Open Access Author Fund
  • ETDS Guide
Copyright Policies

Use Sherpa/Romeo to find publisher copyright policies

Go
Go
  • SPARC Author Addendum Engine
  • National Open Access Policy in Cyprus
Deposit your work to Ktisis
  • Self-archiving. Please sign in to Ktisis.
  • Email your work to:
    library.dspace@cut.ac.cy
  • Contact your subject librarian

Member of

OpenAIREre3dataOpenDOARCOREDART
Cyprus University of Technology
Library and
Information
Services

Copyright © 2022 - Library and Information Services Feedback - Built with DSpace-CRIS - 4Science

  • Accessibility settings
  • Privacy policy
  • End User Agreement
COAR NotifyCOAR Notify