sensors-logo

Journal Browser

Journal Browser

Social Media Sensing: Methodologies and Applications

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Sensor Networks".

Deadline for manuscript submissions: closed (28 February 2023) | Viewed by 7443

Special Issue Editors


E-Mail Website
Guest Editor
Department of Computer Science, University of Pisa, Pisa, Italy
Interests: NFTs; Web3; metaverse; blockchain and cryptocurrencies; decentralized online social networks; peer-to-peer networks; decentralized storages; social network analysis
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Computer Science, University of Pisa, 56127 Pisa, Italy
Interests: dynamics of socioeconomic networks; distributed technologies for the metaverse; blockchain social networking platforms

Special Issue Information

Dear Colleagues,

Online social media (OSM) platforms are becoming one of the most effective tools of communication among people thanks to the fact that more than half of the world’s population are active OSM users. Thanks to the support supplied by OSM platforms, media can travel around the world at lightning speed. OSM can be employed for numerous purposes, including sharing news, providing a personal opinion on a subject, entertaining or educating oneself, and much more.

Therefore, it comes as no surprise that OSM sensing can be used as a source of data to understand people’s opinions as a whole. For example, a company may decide to conduct a series of studies concerning how their products are seen by customers.

On top of that, real-time OSM sensing can also be helpful in critical scenarios, such as in disaster or emergency response. Since OSM sensing is a relatively new topic, many challenges remain unsolved, and a lot more can be achieved, both in terms of methodologies and applications. Additionally, OSM sensing has some significant implications concerning how user privacy is managed and other ethical concerns.

This Special Issue therefore aims to put together original research and review articles on recent advances, technologies, solutions, applications, and new challenges in the field of Social Media Sensing.

Potential topics include but are not limited to:

  • Sensing in social media;
  • Social sensing methodologies;
  • Truth discovery and fake news detection;
  • Business intelligence;
  • Chatbot and Chatscripts;
  • Emotion recognition;
  • Artificial intelligence;
  • Privacy issues of social sensing;
  • Ethics of social sensing;
  • Event forecasting;
  • Sentiment analysis;
  • Social graph analysis;
  • Text analytics;
  • Economics and social effects;
  • Ubiquitous and pervasive crowd-sensing;
  • Semantic web;
  • Reputation and trust;
  • Nowcasting.

Dr. Barbara Guidi
Dr. Michienzi Andrea
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • online social media
  • social data analysis
  • social media analytics
  • social sensing
  • crowdsensing

Published Papers (3 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

19 pages, 2356 KiB  
Article
Flood-Related Multimedia Benchmark Evaluation: Challenges, Results and a Novel GNN Approach
by Thomas Papadimos, Stelios Andreadis, Ilias Gialampoukidis, Stefanos Vrochidis and Ioannis Kompatsiaris
Sensors 2023, 23(7), 3767; https://doi.org/10.3390/s23073767 - 06 Apr 2023
Cited by 2 | Viewed by 1385
Abstract
This paper discusses the importance of detecting breaking events in real time to help emergency response workers, and how social media can be used to process large amounts of data quickly. Most event detection techniques have focused on either images or text, but [...] Read more.
This paper discusses the importance of detecting breaking events in real time to help emergency response workers, and how social media can be used to process large amounts of data quickly. Most event detection techniques have focused on either images or text, but combining the two can improve performance. The authors present lessons learned from the Flood-related multimedia task in MediaEval2020, provide a dataset for reproducibility, and propose a new multimodal fusion method that uses Graph Neural Networks to combine image, text, and time information. Their method outperforms state-of-the-art approaches and can handle low-sample labelled data. Full article
(This article belongs to the Special Issue Social Media Sensing: Methodologies and Applications)
Show Figures

Figure 1

26 pages, 2349 KiB  
Article
Cyber-Physical-Social Awareness Platform for Comprehensive Situation Awareness
by Irfan Baig Mirza, Dimitrios Georgakopoulos and Ali Yavari
Sensors 2023, 23(2), 822; https://doi.org/10.3390/s23020822 - 10 Jan 2023
Cited by 5 | Viewed by 2281
Abstract
Cyber-physical-social computing system integrates the interactions between cyber, physical, and social spaces by fusing information from these spaces. The result of this fusion can be used to drive many applications in areas such as intelligent transportation, smart cities, and healthcare. Situation Awareness was [...] Read more.
Cyber-physical-social computing system integrates the interactions between cyber, physical, and social spaces by fusing information from these spaces. The result of this fusion can be used to drive many applications in areas such as intelligent transportation, smart cities, and healthcare. Situation Awareness was initially used in military services to provide knowledge of what is happening in a combat zone but has been used in many other areas such as disaster mitigation. Various applications have been developed to provide situation awareness using either IoT sensors or social media information spaces and, more recently, using both IoT sensors and social media information spaces. The information from these spaces is heterogeneous and, at their intersection, is sparse. In this paper, we propose a highly scalable, novel Cyber-physical-social Awareness (CPSA) platform that provides situation awareness by using and intersecting information from both IoT sensors and social media. By combining and fusing information from both social media and IoT sensors, the CPSA platform provides more comprehensive and accurate situation awareness than any other existing solutions that rely only on data from social media and IoT sensors. The CPSA platform achieves that by semantically describing and integrating the information extracted from sensors and social media spaces and intersects this information for enriching situation awareness. The CPSA platform uses user-provided situation models to refine and intersect cyber, physical, and social information. The CPSA platform analyses social media and IoT data using pretrained machine learning models deployed in the cloud, and provides coordination between information sources and fault tolerance. The paper describes the implementation and evaluation of the CPSA platform. The evaluation of the CPSA platform is measured in terms of capabilities such as the ability to semantically describe and integrate heterogenous information, fault tolerance, and time constraints such as processing time and throughput when performing real-world experiments. The evaluation shows that the CPSA platform can reliably process and intersect with large volumes of IoT sensor and social media data to provide enhanced situation awareness. Full article
(This article belongs to the Special Issue Social Media Sensing: Methodologies and Applications)
Show Figures

Figure 1

31 pages, 7736 KiB  
Article
A Novel Hybrid Multi-Modal Deep Learning for Detecting Hashtag Incongruity on Social Media
by Sajad Dadgar and Mehdi Neshat
Sensors 2022, 22(24), 9870; https://doi.org/10.3390/s22249870 - 15 Dec 2022
Cited by 2 | Viewed by 2499
Abstract
Hashtags have been an integral element of social media platforms over the years and are widely used by users to promote, organize and connect users. Despite the intensive use of hashtags, there is no basis for using congruous tags, which causes the creation [...] Read more.
Hashtags have been an integral element of social media platforms over the years and are widely used by users to promote, organize and connect users. Despite the intensive use of hashtags, there is no basis for using congruous tags, which causes the creation of many unrelated contents in hashtag searches. The presence of mismatched content in the hashtag creates many problems for individuals and brands. Although several methods have been presented to solve the problem by recommending hashtags based on the users’ interest, the detection and analysis of the characteristics of these repetitive contents with irrelevant hashtags have rarely been addressed. To this end, we propose a novel hybrid deep learning hashtag incongruity detection by fusing visual and textual modality. We fine-tune BERT and ResNet50 pre-trained models to encode textual and visual information to encode textual and visual data simultaneously. We further attempt to show the capability of logo detection and face recognition in discriminating images. To extract faces, we introduce a pipeline that ranks faces based on the number of times they appear on Instagram accounts using face clustering. Moreover, we conduct our analysis and experiments on a dataset of Instagram posts that we collect from hashtags related to brands and celebrities. Unlike the existing works, we analyze these contents from both content and user perspectives and show a significant difference between data. In light of our results, we show that our multimodal model outperforms other models and the effectiveness of object detection in detecting mismatched information. Full article
(This article belongs to the Special Issue Social Media Sensing: Methodologies and Applications)
Show Figures

Figure 1

Back to TopTop