Next Article in Journal
Short-Term Electricity Load Forecasting with Machine Learning
Next Article in Special Issue
CrowdHeritage: Crowdsourcing for Improving the Quality of Cultural Heritage Metadata
Previous Article in Journal
Coming to Grips with Age Prediction on Imbalanced Multimodal Community Question Answering Data
Previous Article in Special Issue
AI-Based Semantic Multimedia Indexing and Retrieval for Social Media on Smartphones
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Information
Volume 12
Issue 2
10.3390/info12020049
information-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Latent Twitter Image Information for Social Analytics

by
Gerasimos Razis
1,*,
Georgios Theofilou
2 and
Ioannis Anagnostopoulos
1
1
Computer Science and Biomedical Informatics Department, University of Thessaly, 35131 Lamia, Greece
2
School of Electrical & Computer Engineering, National Technical University of Athens, 15780 Athens, Greece
*
Author to whom correspondence should be addressed.
Information 2021, 12(2), 49; https://doi.org/10.3390/info12020049
Submission received: 8 December 2020 / Revised: 7 January 2021 / Accepted: 18 January 2021 / Published: 21 January 2021
(This article belongs to the Special Issue Social and Semantic Trends: Tools and Applications)
Browse Figures
Versions Notes

Abstract

The appearance of images in social messages is continuously increasing, along with user engagement with that type of content. Analysis of social images can provide valuable latent information, often not present in the social posts. In that direction, a framework is proposed exploiting latent information from Twitter images, by leveraging the Google Cloud Vision API platform, aiming at enriching social analytics with semantics and hidden textual information. As validated by our experiments, social analytics can be further enriched by considering the combination of user-generated content, latent concepts, and textual data extracted from social images, along with linked data. Moreover, we employed word embedding techniques for investigating the usage of latent semantic information towards the identification of similar Twitter images, thereby showcasing that hidden textual information can improve such information retrieval tasks. Finally, we offer an open enhanced version of the annotated dataset described in this study with the aim of further adoption by the research community.
Keywords: social labeling; Twitter; images; Google Cloud Vision API; OCR; cosine similarity; Word2Vec social labeling; Twitter; images; Google Cloud Vision API; OCR; cosine similarity; Word2Vec

Share and Cite

MDPI and ACS Style

Razis, G.; Theofilou, G.; Anagnostopoulos, I. Latent Twitter Image Information for Social Analytics. Information 2021, 12, 49. https://doi.org/10.3390/info12020049

AMA Style

Razis G, Theofilou G, Anagnostopoulos I. Latent Twitter Image Information for Social Analytics. Information. 2021; 12(2):49. https://doi.org/10.3390/info12020049

Chicago/Turabian Style

Razis, Gerasimos, Georgios Theofilou, and Ioannis Anagnostopoulos. 2021. "Latent Twitter Image Information for Social Analytics" Information 12, no. 2: 49. https://doi.org/10.3390/info12020049

APA Style

Razis, G., Theofilou, G., & Anagnostopoulos, I. (2021). Latent Twitter Image Information for Social Analytics. Information, 12(2), 49. https://doi.org/10.3390/info12020049

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop