Multimodal Data Processing and Semantic Analysis

A special issue of Informatics (ISSN 2227-9709). This special issue belongs to the section "Big Data Mining and Analytics".

Deadline for manuscript submissions: closed (30 November 2021) | Viewed by 14314

Special Issue Editor


E-Mail Website
Guest Editor
School of Journalism and Mass Media Studies, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece
Interests: semantic analysis in audiovisual content; multimedia processing; pattern recognition and classification

Special Issue Information

Dear Colleagues,

Digital content derives, nowadays, from multiple sources and platforms, such as mobile audiovisual capturing devices (smartphones, tablets, laptops), video streaming applications, multimedia and audiovisual productions, social media and interactive web services pursuing audience engagement, etc. In this context, enormous data collections are either formed in cloud infrastructures or stored locally in big databases. The effective management of these data requires the development of intelligent description mechanisms for searching and retrieval purposes, relying on smart metadata processing. Combined with state-of-the-art machine and deep learning architectures, this featured multimodal data processing aims at offering the desired semantic annotating and conceptualization.

This Special Issue Call for Papers (CfP) in “Multimodal Data Processing and Semantic Interpretation” aims at covering all aspects of semantic analysis in digital content, i.e., text, audio, image, and video, such as semantic annotation and processing, multimodal data stream monitoring, audiovisual metadata extraction and management, data summarization, highlighting, and visualization. Multidisciplinary efforts in the field are welcomed, combining natural language processing with machine and deep learning architectures for deploying content classification, intelligent multimodal searching and retrieval, and generally smart services for big data applications. The contributions could include fully implemented systems and their thorough evaluation, concepts for design frameworks, established multimedia system integrations, user studies, as well as work in progress in this scientific field. The main goal of the journal is to publish innovative ideas in this scientific area providing state-of-the-art academic research activities along with multimodal industry implementations.               

The current Special Issue welcomes original research work in, but not limited to, the following topics:

  • Multimedia data description, annotation, and semantic processing;
  • Content-based searching and retrieval;
  • Audiovisual production and QoS/QoE;
  • Machine and deep learning implementations in multimodal content (audio, image, video, text);
  • Sentiment analysis and bias detection in multimedia content;
  • Intelligent systems and multimodal web services;
  • Big data analysis and modeling;
  • Fake content detection and content authentication;
  • Smart tools and applications in multimedia;
  • Semantic analysis, classification, and visualization;
  • Metadata mechanisms;
  • Natural language processing and thematic classification (i.e., hate speech);
  • Geolocation detection.

Dr. Rigas Kotsakis
Guest Editor

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. Informatics is an international peer-reviewed open access quarterly 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 1800 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

  • Audiovisual processing
  • Natural language processing
  • Semantic analysis
  • Semantic classification
  • Multimedia management
  • Multimedia streaming and monitoring
  • Multimedia production
  • Content authentication
  • Multimedia applications

Published Papers (1 paper)

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

Research

21 pages, 1511 KiB  
Article
Hyperparameter Tuning for Machine Learning Algorithms Used for Arabic Sentiment Analysis
by Enas Elgeldawi, Awny Sayed, Ahmed R. Galal and Alaa M. Zaki
Informatics 2021, 8(4), 79; https://doi.org/10.3390/informatics8040079 - 17 Nov 2021
Cited by 137 | Viewed by 13180
Abstract
Machine learning models are used today to solve problems within a broad span of disciplines. If the proper hyperparameter tuning of a machine learning classifier is performed, significantly higher accuracy can be obtained. In this paper, a comprehensive comparative analysis of various hyperparameter [...] Read more.
Machine learning models are used today to solve problems within a broad span of disciplines. If the proper hyperparameter tuning of a machine learning classifier is performed, significantly higher accuracy can be obtained. In this paper, a comprehensive comparative analysis of various hyperparameter tuning techniques is performed; these are Grid Search, Random Search, Bayesian Optimization, Particle Swarm Optimization (PSO), and Genetic Algorithm (GA). They are used to optimize the accuracy of six machine learning algorithms, namely, Logistic Regression (LR), Ridge Classifier (RC), Support Vector Machine Classifier (SVC), Decision Tree (DT), Random Forest (RF), and Naive Bayes (NB) classifiers. To test the performance of each hyperparameter tuning technique, the machine learning models are used to solve an Arabic sentiment classification problem. Sentiment analysis is the process of detecting whether a text carries a positive, negative, or neutral sentiment. However, extracting such sentiment from a complex derivational morphology language such as Arabic has been always very challenging. The performance of all classifiers is tested using our constructed dataset both before and after the hyperparameter tuning process. A detailed analysis is described, along with the strengths and limitations of each hyperparameter tuning technique. The results show that the highest accuracy was given by SVC both before and after the hyperparameter tuning process, with a score of 95.6208 obtained when using Bayesian Optimization. Full article
(This article belongs to the Special Issue Multimodal Data Processing and Semantic Analysis)
Show Figures

Figure 1

Back to TopTop