[go: up one dir, main page]
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.3
2.5
Journals
Applied Sciences
Special Issues
Artificial Intelligence in Complex Networks (2nd Edition)
applsci-logo
Submit to Special Issue Submit Abstract to Special Issue Review for Applied Sciences Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Artificial Intelligence in Complex Networks (2nd Edition)

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: 28 February 2025 | Viewed by 5079

Special Issue Editors

Prof. Dr. Xiaoyang Liu

E-Mail Website
Guest Editor
Department of Computer Science and Engineering, Chongqing University of Technology, Chongqing, China
Interests: complex network; social network analysis; data mining and artificial intelligence
Special Issues, Collections and Topics in MDPI journals
Dr. Giacomo Fiumara

E-Mail Website
Guest Editor
Department of Mathematics and Computer Science, Physical Sciences and Earth Sciences, University of Messina, Messina, Italy
Interests: network science; criminal networks; machine learning; data science; social network analysis
Special Issues, Collections and Topics in MDPI journals
Dr. Pasquale De Meo

E-Mail Website
Guest Editor
Department of Ancient and Modern Civilizations, University of Messina, Messina, Italy
Interests: network science; graph mining; community detection in graphs; recommender systems; trust in virtual communities
Special Issues, Collections and Topics in MDPI journals
Dr. Annamaria Ficara

E-Mail Website
Guest Editor
Department of Mathematics and Informatics, University of Palermo, Palermo, Italy
Interests: social network analysis; complex networks; network science; criminal networks
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues, 

Complex networks offer a unified approach to the study of real-world entities and their connections. Examples of complex networks can be found in many fields of science, such as biological systems, economic systems, and social systems.

In recent years, there has been a significant upsurge of interest in the application of artificial intelligence methods to the study of complex networks. In this context can be ascribed, for example, the suggestion of new connections between entities, the discovery of patterns, and the emergence of structures.

This Special Issue welcomes theoretical and experimental contributions in the area of artificial intelligence applications of complex networks. Areas of interest include, but are not limited to, the following topics:

  • Link prediction;
  • Maximum likelihood;
  • Artificial intelligence methods in complex networks;
  • Artificial intelligence methods in criminal networks;
  • Community detection;
  • Network mining;
  • Methods for the analysis of network structures.

Prof. Dr. Xiaoyang Liu
Dr. Giacomo Fiumara
Dr. Pasquale De Meo
Dr. Annamaria Ficara
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. Applied Sciences 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 2400 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

  • maximum likelihood
  • artificial intelligence methods in complex networks
  • artificial intelligence methods in criminal networks
  • community detection
  • network mining
  • methods for the analysis of network structures

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (4 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Editorial

Jump to: Research

4 pages, 171 KiB  
Editorial
Special Issue “Artificial Intelligence in Complex Networks”
by Xiaoyang Liu
Appl. Sci. 2024, 14(7), 2822; https://doi.org/10.3390/app14072822 - 27 Mar 2024
Viewed by 681
Abstract
Artificial intelligence (AI) in complex networks has made revolutionary breakthroughs in this century, and AI-driven methods are being increasingly integrated into different scientific research [...] Full article
(This article belongs to the Special Issue Artificial Intelligence in Complex Networks (2nd Edition))

Research

Jump to: Editorial

17 pages, 2589 KiB  
Article
Adaptive Evolutionary Computing Ensemble Learning Model for Sentiment Analysis
by Xiao-Yang Liu, Kang-Qi Zhang, Giacomo Fiumara, Pasquale De Meo and Annamaria Ficara
Appl. Sci. 2024, 14(15), 6802; https://doi.org/10.3390/app14156802 - 4 Aug 2024
Viewed by 605
Abstract
Standard machine learning and deep learning architectures have been widely used in the field of sentiment analysis, but their performance is unsatisfactory if the input texts are short (e.g., social media posts). Specifically, the accuracy of standard machine learning methods crucially depends on [...] Read more.
Standard machine learning and deep learning architectures have been widely used in the field of sentiment analysis, but their performance is unsatisfactory if the input texts are short (e.g., social media posts). Specifically, the accuracy of standard machine learning methods crucially depends on the richness and completeness of the features used to represent the texts, and in the case of short messages, it is often difficult to obtain high-quality features. Conversely, methods based on deep learning can achieve better expressiveness, but these methods are computationally demanding and often suffer from over-fitting. This paper proposes a new adaptive evolutionary computational integrated learning model (AdaECELM) to overcome the problems encountered by traditional machine learning and deep learning models in sentiment analysis for short texts. AdaECELM consists of three phases: feature selection, sub classifier training, and global integration learning. First, a grid search is used for feature extraction and selection of term frequency-inverse document frequency (TF-IDF). Second, cuckoo search (CS) is introduced to optimize the combined hyperparameters in the sub-classifier support vector machine (SVM). Finally, the training set is divided into different feature subsets for sub-classifier training, and then the trained sub-classifiers are integrated and learned using the AdaBoost integrated soft voting method. Extensive experiments were conducted on six real polar sentiment analysis data sets. The results show that the AdaECELM model outperforms the traditional ML comparison methods according to evaluation metrics such as accuracy, precision, recall, and F1-score in all cases, and we report an improvement in accuracy exceeding 4.5%, the second-best competitor. Full article
(This article belongs to the Special Issue Artificial Intelligence in Complex Networks (2nd Edition))
►▼ Show Figures

Figure 1

Figure 1
<p>Architecture of AdaECELM for sentiment analysis.</p> Full article ">Figure 2
<p>Feature extraction and sparse matrix normalization.</p> Full article ">Figure 3
<p>Hyperplane diagram. The two dotted lines and dots on either side represent the decision boundaries and different classes of data samples, respectively. The solid line in the middle represents the final partition boundary (hyperplane in higher dimensional space).</p> Full article ">Figure 4
<p>Precision\Recall\F1-score data comparison of imdbs and yelp.</p> Full article ">Figure 5
<p>Precision\Recall\F1-score data comparison of sen_pol and amazon_cells.</p> Full article ">Figure 6
<p>Sensitivity analysis of imdbs data set feature optimization.</p> Full article ">Figure 6 Cont.
<p>Sensitivity analysis of imdbs data set feature optimization.</p> Full article ">
26 pages, 14493 KiB  
Article
A Novel Method to Identify Key Nodes in Complex Networks Based on Degree and Neighborhood Information
by Na Zhao, Shuangping Yang, Hao Wang, Xinyuan Zhou, Ting Luo and Jian Wang
Appl. Sci. 2024, 14(2), 521; https://doi.org/10.3390/app14020521 - 7 Jan 2024
Cited by 3 | Viewed by 1392
Abstract
One key challenge within the domain of network science is accurately finding important nodes within a network. In recent years, researchers have proposed various node centrality indicators from different perspectives. However, many existing methods have their limitations. For instance, certain approaches lack a [...] Read more.
One key challenge within the domain of network science is accurately finding important nodes within a network. In recent years, researchers have proposed various node centrality indicators from different perspectives. However, many existing methods have their limitations. For instance, certain approaches lack a balance between time efficiency and accuracy, while the majority of research neglects the significance of local clustering coefficients, a crucial node property. Thus, this paper introduces a centrality metric called DNC (degree and neighborhood information centrality) that considers both node degree and local clustering coefficients. The combination of these two aspects provides DNC with the ability to create a more comprehensive measure of nodes’ local centrality. In addition, in order to obtain better performance in different networks, this paper sets a tunable parameter α to control the effect of neighbor information on the importance of nodes. Subsequently, the paper proceeds with a sequence of experiments, including connectivity tests, to validate the efficacy of DNC. The results of the experiments demonstrate that DNC captures more information and outperforms the other eight centrality metrics. Full article
(This article belongs to the Special Issue Artificial Intelligence in Complex Networks (2nd Edition))
►▼ Show Figures

Figure 1

Figure 1
<p>Karate network. The numbers in the figure indicate the node numbers.</p> Full article ">Figure 2
<p>Subfigures (<b>a</b>–<b>d</b>) represent the correlation matrices between DNC and the baseline methods in the Adjnoun, Celegans, Yeast, and Hamsterster networks. The correlation coefficients between the two methods are mathematically expressed by the corresponding rows and columns. The first row represents the correlation coefficients between DNC and the baseline methods, while the second row represents the correlation coefficients between CI and the remaining methods. The black numbers in the figure indicate that the two methods have low correlation.</p> Full article ">Figure 3
<p>Subfigures (<b>a</b>), (<b>b</b>), (<b>c</b>), and (<b>d</b>) respectively represent the performance of DNC and the baseline methods in terms of accuracy on the Dmela, Kohonen, Yeast, and Vote networks. The x-axis of each subfigure represents the sequential removal of nodes according to DNC or the baseline methods. The y-axis measures the degree of network collapse, with a faster descent indicating greater accuracy for the method.</p> Full article ">Figure 4
<p>Subfigures (<b>a</b>), (<b>b</b>), (<b>c</b>), and (<b>d</b>) respectively depict the rank distribution plots of DNC and the baseline methods on the Dmela, Email, Yeast, and Hamsterster networks. The x-axis of each subfigure represents the ranking of nodes, while the y-axis represents the count of nodes with the same ranking.</p> Full article ">Figure 5
<p>Subfigures (<b>a</b>), (<b>b</b>), (<b>c</b>), and (<b>d</b>) respectively illustrate the CPU time comparison between DNC and the baseline methods on the Adjnoun, Jazz, Dolphins, and USAir97 networks.</p> Full article ">Figure 6
<p>Performance comparison of DNC and the baseline methods on the BA network.</p> Full article ">Figure 7
<p>Performance comparison of DNC and the baseline methods on the ER network.</p> Full article ">Figure 8
<p>Performance comparison of DNC and the baseline methods on the WS network.</p> Full article ">Figure 9
<p>Rank distribution plots of DNC and the baseline methods on BA networks.</p> Full article ">Figure 10
<p>Rank distribution plots of DNC and the baseline methods on ER networks.</p> Full article ">Figure 11
<p>Rank distribution plots of DNC and the baseline methods on WS networks.</p> Full article ">Figure A1
<p>Subfigures (<b>a</b>–<b>l</b>) represent the correlation matrices between DNC and baseline methods on Adjnoun, Dolphins, Polbooks, Jazz, Celegans, USAir97, Dmela, Vote, Email, Yeast, Hamsterster, Kohonen networks, respectively.</p> Full article ">Figure A1 Cont.
<p>Subfigures (<b>a</b>–<b>l</b>) represent the correlation matrices between DNC and baseline methods on Adjnoun, Dolphins, Polbooks, Jazz, Celegans, USAir97, Dmela, Vote, Email, Yeast, Hamsterster, Kohonen networks, respectively.</p> Full article ">Figure A1 Cont.
<p>Subfigures (<b>a</b>–<b>l</b>) represent the correlation matrices between DNC and baseline methods on Adjnoun, Dolphins, Polbooks, Jazz, Celegans, USAir97, Dmela, Vote, Email, Yeast, Hamsterster, Kohonen networks, respectively.</p> Full article ">Figure A2
<p>Subfigures (<b>a</b>–<b>l</b>) represent the accuracy performance of DNC versus baseline methods on Adjnoun, Dmela, Celegans, Email, Hamsterster, Kohonen, Jazz, Vote, Polbooks, Dolphins, Yeast, USAir97 networks, respectively.</p> Full article ">Figure A2 Cont.
<p>Subfigures (<b>a</b>–<b>l</b>) represent the accuracy performance of DNC versus baseline methods on Adjnoun, Dmela, Celegans, Email, Hamsterster, Kohonen, Jazz, Vote, Polbooks, Dolphins, Yeast, USAir97 networks, respectively.</p> Full article ">Figure A2 Cont.
<p>Subfigures (<b>a</b>–<b>l</b>) represent the accuracy performance of DNC versus baseline methods on Adjnoun, Dmela, Celegans, Email, Hamsterster, Kohonen, Jazz, Vote, Polbooks, Dolphins, Yeast, USAir97 networks, respectively.</p> Full article ">Figure A3
<p>Subfigures (<b>a</b>–<b>l</b>) represent the rank distribution plots of DNC and baseline methods on Adjnoun, Dmela, Celegans, Dolphins, Email, Hamsterster, Jazz, Kohonen, Yeast, Polbooks, USAir97, and Vote networks, respectively.</p> Full article ">Figure A3 Cont.
<p>Subfigures (<b>a</b>–<b>l</b>) represent the rank distribution plots of DNC and baseline methods on Adjnoun, Dmela, Celegans, Dolphins, Email, Hamsterster, Jazz, Kohonen, Yeast, Polbooks, USAir97, and Vote networks, respectively.</p> Full article ">
21 pages, 2866 KiB  
Article
Sentiment Analysis of Students’ Feedback on E-Learning Using a Hybrid Fuzzy Model
by Maryam Alzaid and Fethi Fkih
Appl. Sci. 2023, 13(23), 12956; https://doi.org/10.3390/app132312956 - 4 Dec 2023
Cited by 3 | Viewed by 1503
Abstract
It is crucial to analyze opinions about the significant shift in education systems around the world, because of the widespread use of e-learning, to gain insight into the state of education today. A particular focus should be placed on the feedback from students [...] Read more.
It is crucial to analyze opinions about the significant shift in education systems around the world, because of the widespread use of e-learning, to gain insight into the state of education today. A particular focus should be placed on the feedback from students regarding the profound changes they experience when using e-learning. In this paper, we propose a model that combines fuzzy logic with bidirectional long short-term memory (BiLSTM) for the sentiment analysis of students’ textual feedback on e-learning. We obtained this feedback from students’ tweets expressing their opinions about e-learning. There were some ambiguous characteristics in terms of the writing style and language used in the collected feedback. It was written informally and not in adherence to standardized Arabic language writing rules by using the Saudi dialects. The proposed model benefits from the capabilities of the deep neural network BiLSTM to learn and also from the ability of fuzzy logic to handle uncertainties. The proposed models were evaluated using the appropriate evaluation metrics: accuracy, F1-score, precision, and recall. The results showed the effectiveness of our proposed model and that it worked well for analyzing opinions obtained from Arabic texts written in Saudi dialects. The proposed model outperformed the compared models by obtaining an accuracy of 86% and an F1-score of 85%. Full article
(This article belongs to the Special Issue Artificial Intelligence in Complex Networks (2nd Edition))
►▼ Show Figures

Figure 1

Figure 1
<p>Overall methodology.</p> Full article ">Figure 2
<p>Distribution of sentiment.</p> Full article ">Figure 3
<p>Data preprocessing steps.</p> Full article ">Figure 4
<p>The architecture of the proposed model.</p> Full article ">Figure 5
<p>Gaussian membership function.</p> Full article ">Figure 6
<p>Comparative results for the proposed model and the standalone BiLSTM.</p> Full article ">Figure 7
<p>Comparative results for the proposed model and machine learning models.</p> Full article ">Figure 8
<p>Word cloud of the most frequent words in the negative opinions.</p> Full article ">
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-4
Back to TopTop