Applied Artificial Intelligence Approach: Intelligent Data Processing and Mining with Online Behaviors

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: 20 June 2024 | Viewed by 1020

Special Issue Editors

Prof. Dr. Haihong E
E-Mail Website
Guest Editor
School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China
Interests: big data analysis; knowledge graph; intelligent data processing
Dr. Yifan Zhu
E-Mail Website
Guest Editor
School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China
Interests: data mining; recommendation systems; knowledge graph
Dr. Qika Lin
E-Mail Website
Guest Editor
Saw Swee Hock School of Public Health, National University of Singapore, Singapore 117549, Singapore
Interests: logical reasoning; natural language processing; multimodal representation and reasoning
Dr. Kaize Shi
E-Mail Website
Guest Editor
Data Science and Machine Intelligence Lab, University of Technology Sydney, Sydney, NSW 2007, Australia
Interests: data mining; social computing; natural language processing

Special Issue Information

Dear Colleagues,

The COVID-19 outbreak has profoundly changed the way people work, live, and study in recent years. To maintain social distancing, a great deal of remote technology is used as a productivity tool. Large-scale offline activities are rapidly being transformed into online or hybrid events, which introduces opportunities as well as challenges.

From the point of view of information transmission, online activities have greatly extended the distance of communication while inevitably losing information of various modes. That is, although visual, auditory and other information can be transmitted in collaboration, there are still studies showing that a lot of potential perceptual information has not been well encoded in online platforms. Furthermore, the cognitive process of traditional interactions has also been changed in that online users acquire knowledge in a more personalized, customized, and behavioral approach. However, due to the lack of learning paradigms in these new situations, current models and platforms generally face difficulties such as cognitive trek and high dropout rates. Therefore, it is urgent to invent more comprehensive, personalized, and explainable AI methods to re-understand the patterns and cognitive processes of user profiling after the change.

In recent years, the advance of deep representation learning and other AI methods has introduced a new angle to this problem in many respects, such as graph neural networks, pretrained language and multimodal models, deep reinforcement learning, etc. In addition to the incredible achievements that have been made, scientists are still working towards revealing the essence of different learning process. From the perspective of AI, this intelligence-based approach provides the potential to make AI-based systems not only intelligent but also knowledgeable, which is also crucial in explainable artificial intelligence (XAI). Furthermore, machine intelligence-based models also help to recognize the psychological and cognitive patterns of users in their interaction process. We believe that fundamental innovation via the use of AI could immensely promote the understanding of user behavior, emotion, attention, and knowledge acquisition. Thus, we hope to invite submissions of research articles that focus on intelligent data processing and mining with online behaviors from the view of AI and machine learning.

This proposed Special Issue has the following sub-topics:

  • AI theory for behavioral analysis technology:
    • Graph and network theory for the learning process;
    • New representation learning paradigms;
    • Explainable AI and its mechanism;
    • Contrastive analysis between machine learning and human learning;
    • Machine intelligence-driven psychological and cognitive pattern recognition.
  • Intelligence driven methods for online behavioral data mining:
    • Computer version-based user attention and emotion tracing;
    • Multi-modal, multi-sourced heterogeneous information fusion;
    • Intelligence-guided reasoning and searching of knowledge concepts;
    • AI-powered learning object generation;
    • Recommendation and retrieval for online objects;
    • Knowledge-tracing techniques;
    • Neural network structures for application;
    • Explainable AI for user profiling;
  • Applications with intelligence-driven technology:
    • Domain- and subject knowledge-specific application;
    • The use pf intelligent tools for large-scale application;
    • New human–computer interaction approaches;
    • Art driven by AI for intelligent simulation and digital creativity.
  • Surveys on the above topics.

Prof. Dr. Haihong E
Dr. Yifan Zhu
Dr. Qika Lin
Dr. Kaize Shi
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. Electronics 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

  • online mining
  • behavior mining
  • intelligent information processing

Published Papers (2 papers)

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

Research

17 pages, 652 KiB  
Article
A Multi-View Temporal Knowledge Graph Reasoning Framework with Interpretable Logic Rules and Feature Fusion
Electronics 2024, 13(4), 742; https://doi.org/10.3390/electronics13040742 - 12 Feb 2024
Viewed by 356
Abstract
A temporal knowledge graph represents temporal information between entities in a multi-relational graph. Its reasoning aims to infer and predict potential links among entities. Predicting time-aware entities is a challenging task due to significant differences in entity appearances over time, such as different [...] Read more.
A temporal knowledge graph represents temporal information between entities in a multi-relational graph. Its reasoning aims to infer and predict potential links among entities. Predicting time-aware entities is a challenging task due to significant differences in entity appearances over time, such as different timestamps and frequencies. Current embedding-based similarity-matching methods have been introduced for predicting temporal facts. However, they lack deterministic logical explainability and cannot model the dynamic evolution of entities over time. To address these challenges, we propose a novel framework for temporal knowledge graph reasoning based on multi-view feature fusion (MVFF). First, MVFF extracts logical rules and uses the Gumbel-Softmax trick to sample high-quality rules. Second, it integrates logical rules, temporal quadruples, and factual triples to capture semantic features, temporal information, and structural information to solve link prediction tasks. Through experiments on four benchmark datasets, we show that MVFF outperforms state-of-the-art methods, providing not only better performance but also interpretable results. Full article
Show Figures

Figure 1

12 pages, 1521 KiB  
Article
A Job Recommendation Model Based on a Two-Layer Attention Mechanism
Electronics 2024, 13(3), 485; https://doi.org/10.3390/electronics13030485 - 24 Jan 2024
Viewed by 428
Abstract
In the field of job recruitment, traditional recommendation methods only rely on users’ rating data of positions for information matching. This simple strategy has problems such as low utilization of multi-source heterogeneous data and difficulty in mining relevant information between recruiters and applicants. [...] Read more.
In the field of job recruitment, traditional recommendation methods only rely on users’ rating data of positions for information matching. This simple strategy has problems such as low utilization of multi-source heterogeneous data and difficulty in mining relevant information between recruiters and applicants. Therefore, this paper proposes a recurrent neural network model based on a two-layer attention mechanism. The model first improves the entity representation of recruiters and applicants through user behavior, company-related knowledge and other information. The entities and their combinations are then mapped to the vector space using one-hot and TransR methods, and a recurrent neural network with a two-layer attention mechanism is used to obtain their potential interests from the click sequence, and then a recommendation list is generated. The experimental results show that this model achieves better results than previous models. Full article
Show Figures

Figure 1

Back to TopTop