Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
9.8
4.4
Journals
BDCC
Special Issues
Artificial Intelligence (AI) and Natural Language Processing (NLP)
share announcement

Artificial Intelligence (AI) and Natural Language Processing (NLP)

A special issue of Big Data and Cognitive Computing (ISSN 2504-2289).

Deadline for manuscript submissions: 20 July 2026 | Viewed by 20406

Special Issue Editors

Dr. Sardar Jaf

E-Mail Website
Guest Editor
School of Computer Science, University of Sunderland, Sunderland SR1 3SD, UK
Interests: artificial intelligence; natural language processing; data science; large language model; NLP application; AI ethics and privacy issues; cybersecurity
Special Issues, Collections and Topics in MDPI journals
Dr. Basel Barakat

E-Mail Website
Guest Editor
School of Computing, Goldsmiths University of London, London SE14 6NW, UK
Interests: artificial intelligence; natural language processing; time-series forecasting; algorithms; Internet of Things (IoT) systems; real-time communication systems; healthcare technology innovation
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Yongqiang Cheng

E-Mail Website
Guest Editor
School of Computer Science, University of Sunderland, Sunderland SR1 3SD, UK
Interests: smart systems and digital healthcare; artificial intelligence; machine learning; wireless sensor network
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Artificial intelligence (AI) and natural language processing (NLP) are at the forefront of transformative technologies reshaping the way we interact with computers and automated machines. AI encompasses the broader discipline of developing systems capable of performing tasks that typically require human intelligence, such as reasoning, decision-making, categorization, prediction, and learning. NLP, a subfield of AI, focuses on enabling computers to understand, analyze, translate or interpret, generate, and respond to human language in a meaningful way.

Recent advancements in machine learning, especially in deep learning, and in large language models have significantly enhanced the capabilities of NLP applications, which range from real-time translation and use in dialogue systems and human–machine conversations to intelligent virtual assistance and automated content generation. These developments are opening new frontiers in many non-computing disciplines such as healthcare, education, business, economy, politics, manufacturing, etc.

For this Special Issue, we invite researchers, practitioners, and academics to contribute original research articles, reviews, and case studies that explore the latest innovations, challenges, and future directions in NLP and AI. Submissions may include theoretical insights, practical implementations, interdisciplinary approaches, and novel applications. This Special Issue will cover the following topics (though this list is not exhaustive):

  1. Machine Learning and Deep Learning for NLP
    • Machine learning and deep learning methods;
    • Implementation, integration, testing, and deployment issues of AI and NLP systems;
    • Transfer learning and pre-training techniques.
  2. Language Modeling and Generation
    • Text summarization;
    • Machine translation;
    • Text generation and completion.
  3. Speech and Audio Processing
    • Speech recognition and synthesis;
    • Multimodal NLP (audio + text).
  4. Semantic Analysis
    • Named entity recognition (NER);
    • Word sense disambiguation;
    • Semantic similarity and entailment.
  5. Information Extraction and Retrieval
    • Knowledge graph construction;
    • Question answering systems;
    • Search engines and semantic search.
  6. Emerging Topics
    • Large language models (LLMs);
    • Scaling laws, model compression, prompt engineering;
    • Safety, alignment, and interpretability.
  7. Multimodal AI
    • Vision–language integration (e.g., image captioning, VQA);
    • Cross-modal retrieval.
  8. Ethics, Fairness, and Bias in NLP/AI
    • Algorithmic fairness;
    • Mitigation of harmful content;
    • Transparency and accountability.
  9. Low-resource and Multilingual NLP
    • Zero-shot and few-shot learning;
    • Cross-lingual transfer.
  10. Human–AI Collaboration
    • Co-creative systems;
    • Conversational agents and chatbots;
    • Explainable AI in NLP.
  11. Application-Focused Areas
    • Healthcare;
    • Clinical NLP;
    • Medical report generation and classification;
    • NLP for finance.
  12. Education and E-learning
    • Automated essay scoring;
    • Intelligent tutoring systems;
    • Assessment and plagiarism.
  13. Legal and Financial AI
    • Contract analysis;
    • Document classification and summarization;
    • Privacy, security, trust, and ethical issues in AI;
    • Legal complications on AI models.
  14. Social Media and Sentiment Analysis
    • Misinformation detection;
    • Opinion mining.
  15. Robotics and Human–Robot Interaction
    • Natural language instruction;
    • Context-aware dialogue systems.

You may choose our Joint Special Issue in Future Internet.

Dr. Sardar Jaf
Dr. Basel Barakat
Prof. Dr. Yongqiang Cheng
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 250 words) can be sent to the Editorial Office for assessment.

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. Big Data and Cognitive Computing is an international peer-reviewed open access monthly 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

  • artificial intelligence
  • AI
  • natural language processing
  • NLP
  • language models
  • large language model
  • speech processing
  • text processing
  • language processing

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.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

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

Published Papers (8 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:

Research

Jump to: Review, Other

25 pages, 6493 KB  
Article
A Dynamic Prompt-Based Logic-Aided Compliance Checker
by Wenxi Sheng, Chi Wei, Yinuo Zhang, Bowen Zhang and Jingyun Sun
Big Data Cogn. Comput. 2026, 10(3), 95; https://doi.org/10.3390/bdcc10030095 - 21 Mar 2026
Viewed by 477
Abstract
Text-based automatic compliance checking (ACC) employs natural language processing technologies to scrutinize a corporation’s business documents, ensuring adherence to related normative texts. The current methods fall into two primary categories: symbol-based and embedding-based approaches. Symbol-based methods, noted for their accuracy and transparent processing, [...] Read more.
Text-based automatic compliance checking (ACC) employs natural language processing technologies to scrutinize a corporation’s business documents, ensuring adherence to related normative texts. The current methods fall into two primary categories: symbol-based and embedding-based approaches. Symbol-based methods, noted for their accuracy and transparent processing, suffer from limited versatility. Conversely, embedding-based methods operate independently of expert knowledge yet often yield challenging-to-interpret results and require substantial volumes of annotated data. While both types of methods exhibit advantages in different aspects, the current research fails to combine these advantages effectively. Therefore, the existing methods fail to balance interpretability, generalization ability, and accuracy, which are key requirements for practical compliance systems. To address this problem, we introduce a novel approach termed the Dynamic Prompt-based Logic-Aided Compliance Checker (DPLACC), which is grounded in the prompt learning framework. This method initially parses target texts, transforming the results into first-order logical expressions. It subsequently retrieves pertinent knowledge from a knowledge graph, converting the knowledge into analogous first-order logical expressions. These expressions are then encoded into a global semantic vector via a pre-trained first-order logistic encoder. Ultimately, the semantics of expressions and initial texts are amalgamated within the prompt template, facilitating the logical knowledge enhancement of model reasoning. Experiments on Chinese and English datasets demonstrate that DPLACC comprehensively outperforms existing methods based solely on symbols or embeddings in terms of accuracy, precision, recall, and F1 score and significantly surpasses current mainstream large language models. Furthermore, DPLACC exhibits enhanced interpretability and reduced data dependence, maintaining 70% checking accuracy with as few as ten training samples. This capability allows DPLACC to be rapidly deployed in data-scarce real-world scenarios with minimal annotation overhead, thus offering a practical pathway toward the scalable implementation of compliance inspection systems. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) and Natural Language Processing (NLP))
►▼ Show Figures

Figure 1

26 pages, 1059 KB  
Article
Validating the Effectiveness of Fine-Tuning for Semantic Classification of Japanese Katakana Words: An Analysis of Frequency and Polysemy Effects on Accuracy
by Kazuki Kodaki and Minoru Sasaki
Big Data Cogn. Comput. 2026, 10(3), 67; https://doi.org/10.3390/bdcc10030067 - 26 Feb 2026
Viewed by 574
Abstract
In semantic classification of katakana words using large language models and pre-trained language models, semantic divergences from original English meanings, such as those found in Wasei-Eigo which is Japanese-made English, and the inherent sense ambiguity in katakana words may affect model accuracy. To [...] Read more.
In semantic classification of katakana words using large language models and pre-trained language models, semantic divergences from original English meanings, such as those found in Wasei-Eigo which is Japanese-made English, and the inherent sense ambiguity in katakana words may affect model accuracy. To analyze the impact of these loanword semantic characteristics on classification accuracy, we created a large-scale dataset from the Balanced Corpus of Contemporary Written Japanese. We extracted 403,819 sentences covering 230 katakana words defined in dictionaries and suitable for word sense disambiguation tasks, and used the gpt-4.1-mini model to predict the meaning of the target words based on their context, to create annotation data. We then fine-tuned the pre-trained language model DeBERTa V3 with this data. We compared baseline and fine-tuned model accuracy, dividing data into four quadrants based on frequency and polysemy to conduct statistical analysis and explore strategies for improving accuracy. We also tested the hypothesis that high-frequency, low-polysemy words would achieve the highest accuracy, while low-frequency, high-polysemy words would achieve the lowest. As a result, the fine-tuned model showed an average accuracy improvement of approximately 53% compared to the baseline model. As hypothesized, high-frequency, low-polysemy words achieved the highest accuracy (93.93%), while low-frequency, high-polysemy words achieved the lowest (81.14%). Our analysis quantitatively revealed that both frequency and polysemy contributed to accuracy improvement, but polysemy had a greater impact on accuracy than frequency. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) and Natural Language Processing (NLP))
►▼ Show Figures

Figure 1

22 pages, 820 KB  
Article
CBR2: A Case-Based Reasoning Framework with Dual Retrieval Guidance for Few-Shot KBQA
by Xinyu Hu, Tong Li, Lingtao Xue, Zhipeng Du, Kai Huang, Gang Xiao and He Tang
Big Data Cogn. Comput. 2026, 10(1), 17; https://doi.org/10.3390/bdcc10010017 - 4 Jan 2026
Viewed by 853
Abstract
Recent advances in large language models (LLMs) have driven substantial progress in knowledge base question answering (KBQA), particularly under few-shot settings. However, symbolic program generation remains challenging due to its strict structural constraints and high sensitivity to generation errors. Existing few-shot methods often [...] Read more.
Recent advances in large language models (LLMs) have driven substantial progress in knowledge base question answering (KBQA), particularly under few-shot settings. However, symbolic program generation remains challenging due to its strict structural constraints and high sensitivity to generation errors. Existing few-shot methods often rely on multi-turn strategies, such as rule-based step-by-step reasoning or iterative self-correction, which introduce additional latency and exacerbate error propagation. We present CBR2, a case-based reasoning framework with dual retrieval guidance for single-pass symbolic program generation. Instead of generating programs interactively, CBR2 constructs a unified structure-aware prompt that integrates two complementary types of retrieval: (1) structured knowledge from ontologies and factual triples, and (2) reasoning exemplars retrieved via semantic and function-level similarity. A lightweight similarity model is trained to retrieve structurally aligned programs, enabling effective transfer of abstract reasoning patterns. Experiments on KQA Pro and MetaQA demonstrate that CBR2 achieves significant improvements in both accuracy and syntactic robustness. Specifically on KQA Pro, it boosts Hits@1 from 72.70% to 82.13% and reduces syntax errors by 25%, surpassing the previous few-shot state-of-the-art. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) and Natural Language Processing (NLP))
►▼ Show Figures

Figure 1

23 pages, 2741 KB  
Article
Subjective Evaluation of Operator Responses for Mobile Defect Identification in Remanufacturing: Application of NLP and Disagreement Tagging
by Abbirah Ahmed, Reenu Mohandas, Arash Joorabchi and Martin J. Hayes
Big Data Cogn. Comput. 2025, 9(12), 312; https://doi.org/10.3390/bdcc9120312 - 4 Dec 2025
Viewed by 704
Abstract
In the context of remanufacturing, particularly mobile device refurbishing, effective operator training is crucial for accurate defect identification and process inspection efficiency. This study examines the application of Natural Language Processing (NLP) techniques to evaluate operator expertise based on subjective textual responses gathered [...] Read more.
In the context of remanufacturing, particularly mobile device refurbishing, effective operator training is crucial for accurate defect identification and process inspection efficiency. This study examines the application of Natural Language Processing (NLP) techniques to evaluate operator expertise based on subjective textual responses gathered during a defect analysis task. Operators were asked to describe screen defects using open-ended questions, and their responses were compared with expert responses to evaluate their accuracy and consistency. We employed four NLP models, including finetuned Sentence-BERT (SBERT), pre-trained SBERT, Word2Vec, and Dice similarity, to determine their effectiveness in interpreting short, domain-specific text. A novel disagreement tagging framework was introduced to supplement traditional similarity metrics with explainable insights. This framework identifies the root causes of model–human misalignment across four categories: defect type, severity, terminology, and location. Results show that a finetuned SBERT model significantly outperforms other models by achieving Pearsons’s correlation of 0.93 with MAE and RMSE scores of 0.07 and 0.12, respectively, providing more accurate and context-aware evaluations. In contrast, other models exhibit limitations in semantic understanding and consistency. The results highlight the importance of finetuning NLP models for domain-specific applications and demonstrate how qualitative tagging methods can enhance interpretability and model debugging. This combined approach indicates a scalable and transparent methodology for the evaluation of operator responses, supporting the development of more effective training programmes in industrial settings where remanufacturing and sustainability generally are a key performance metric. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) and Natural Language Processing (NLP))
►▼ Show Figures

Figure 1

26 pages, 4013 KB  
Article
Music Genre Classification Using Prosodic, Stylistic, Syntactic and Sentiment-Based Features
by Erik-Robert Kovacs and Stefan Baghiu
Big Data Cogn. Comput. 2025, 9(11), 296; https://doi.org/10.3390/bdcc9110296 - 19 Nov 2025
Viewed by 3068
Abstract
Romanian popular music has had a storied history across the last century and a half. Incorporating different influences at different times, today it boasts a wide range of both autochthonous and imported genres, such as traditional folk music, rock, rap, pop, and manele, [...] Read more.
Romanian popular music has had a storied history across the last century and a half. Incorporating different influences at different times, today it boasts a wide range of both autochthonous and imported genres, such as traditional folk music, rock, rap, pop, and manele, to name a few. We aim to trace the linguistic differences between the lyrics of these genres using natural language processing and a computational linguistics approach by studying the prosodic, stylistic, syntactic, and sentiment-based features of each genre. For this purpose, we have crawled a dataset of ~14,000 Romanian songs from publicly available websites along with the user-provided genre labels, and characterized each song and each genre, respectively, with regard to these features, discussing similarities and differences. We improve on existing tools for Romanian language natural language processing by building a lexical analysis library well suited to song lyrics or poetry which encodes a set of 17 linguistic features. In addition, we build lexical analysis tools for profanity-based features and improve the SentiLex sentiment analysis library by manually rebalancing its lexemes to overcome the limitations introduced by it having been machine translated into Romanian. We estimate the accuracy gain using a benchmark Romanian sentiment analysis dataset and register a 25% increase in accuracy over the SentiLex baseline. The contribution is meant to describe the characteristics of the Romanian expression of autochthonous as well as international genres and provide technical support to researchers in natural language processing, musicology or the digital humanities in studying the lyrical content of Romanian music. We have released our data and code for research use. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) and Natural Language Processing (NLP))
►▼ Show Figures

Figure 1

30 pages, 569 KB  
Article
Demo-ToT: Enhancing the Reasoning Capabilities of AI Agent via Improved Demonstrations Retrieval Strategy
by Jiahui Li, Bangbang Ren, Mengmeng Zhang and Honghui Chen
Big Data Cogn. Comput. 2025, 9(11), 276; https://doi.org/10.3390/bdcc9110276 - 2 Nov 2025
Viewed by 1461
Abstract
Innovative reasoning frameworks have been proposed to enhance the reasoning capabilities of AI agents, improving their performance in various tasks. However, most existing research has focused on enhancing designing frameworks for LLMs, with limited attention on leveraging in-context learning to boost their reasoning [...] Read more.
Innovative reasoning frameworks have been proposed to enhance the reasoning capabilities of AI agents, improving their performance in various tasks. However, most existing research has focused on enhancing designing frameworks for LLMs, with limited attention on leveraging in-context learning to boost their reasoning power. This paper proposes a novel approach, Demo-ToT, which enhances the Tree-of-Thought (ToT) reasoning framework by dynamically retrieving relevant demonstrations to improve reasoning accuracy. Various demonstration retrieval strategies, including vector similarity, sparse retrieval, and string similarity, were explored to identify the most effective methods for optimizing LLM performance. Experiments conducted across multiple benchmarks and language models of varying sizes demonstrated that Demo-ToT substantially enhanced the reasoning ability of smaller LLMs, achieving performance comparable to or even surpassing that of much larger models such as GPT-4. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) and Natural Language Processing (NLP))
►▼ Show Figures

Figure 1

Review

Jump to: Research, Other

29 pages, 1978 KB  
Review
Large Language Models in Mechanical Engineering: A Scoping Review of Applications, Challenges, and Future Directions
by Christopher Baker, Karen Rafferty and Mark Price
Big Data Cogn. Comput. 2025, 9(12), 305; https://doi.org/10.3390/bdcc9120305 - 30 Nov 2025
Viewed by 3018
Abstract
Following PRISMA-ScR guidelines, this scoping review systematically maps the landscape of Large Language Models (LLMs) in mechanical engineering. A search of four major databases (Scopus, IEEE Xplore, ACM Digital Library, Web of Science) and a rigorous screening process yielded 66 studies for final [...] Read more.
Following PRISMA-ScR guidelines, this scoping review systematically maps the landscape of Large Language Models (LLMs) in mechanical engineering. A search of four major databases (Scopus, IEEE Xplore, ACM Digital Library, Web of Science) and a rigorous screening process yielded 66 studies for final analysis. The findings reveal a nascent, rapidly accelerating field, with over 68% of publications from 2024 (representing a year-on-year growth of 150% from 2023 to 2024), and applications concentrated on front-end design processes like conceptual design and Computer-Aided Design (CAD) generation. The technological landscape is dominated by OpenAI’s GPT-4 variants. A persistent challenge identified is weak spatial and geometric reasoning, shifting the primary research bottleneck from traditional data scarcity to inherent model limitations. This, alongside reliability concerns, forms the main barrier to deeper integration into engineering workflows. A consensus on future directions points to the need for specialized datasets, multimodal inputs to ground models in engineering realities, and robust, engineering-specific benchmarks. This review concludes that LLMs are currently best positioned as powerful ‘co-pilots’ for engineers rather than autonomous designers, providing an evidence-based roadmap for researchers, practitioners, and educators. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) and Natural Language Processing (NLP))
►▼ Show Figures

Figure 1

Other

Jump to: Research, Review

90 pages, 1718 KB  
Systematic Review
A Systematic Literature Review of Retrieval-Augmented Generation: Techniques, Metrics, and Challenges
by Andrew Brown, Muhammad Roman and Barry Devereux
Big Data Cogn. Comput. 2025, 9(12), 320; https://doi.org/10.3390/bdcc9120320 - 12 Dec 2025
Cited by 7 | Viewed by 9097
Abstract
Background: Retrieval-augmented generation (RAG) aims to reduce hallucinations and outdated knowledge by grounding LLM outputs in retrieved evidence, but empirical results are scattered across tasks, systems, and metrics, limiting cumulative insight. Objective: We aimed to synthesise empirical evidence on RAG effectiveness versus parametric-only [...] Read more.
Background: Retrieval-augmented generation (RAG) aims to reduce hallucinations and outdated knowledge by grounding LLM outputs in retrieved evidence, but empirical results are scattered across tasks, systems, and metrics, limiting cumulative insight. Objective: We aimed to synthesise empirical evidence on RAG effectiveness versus parametric-only baselines, map datasets/architectures/evaluation practices, and surface limitations and research gaps. Methods: This systematic review was conducted and reported in accordance with PRISMA 2020. We searched the ACM Digital Library, IEEE Xplore, Scopus, ScienceDirect, and DBLP; all sources were last searched on 13 May 2025. This included studies from January 2020–May 2025 that addressed RAG or similar retrieval-supported systems producing text output, met citation thresholds (≥15 for 2025; ≥30 for 2024 or earlier), and offered original contributions; excluded non-English items, irrelevant works, duplicates, and records without accessible full text. Bias was appraised with a brief checklist; screening used one reviewer with an independent check and discussion. LLM suggestions were advisory only; 2025 citation thresholds were adjusted to limit citation-lag. We used a descriptive approach to synthesise the results, organising studies by themes aligned to RQ1–RQ4 and reporting summary counts/frequencies; no meta-analysis was undertaken due to heterogeneity of designs and metrics. Results: We included 128 studies spanning knowledge-intensive tasks (35/128; 27.3%), open-domain QA (20/128; 15.6%), software engineering (13/128; 10.2%), and medical domains (11/128; 8.6%). Methods have shifted from DPR + seq2seq baselines to modular, policy-driven RAG with hybrid/structure-aware retrieval, uncertainty-triggered loops, memory, and emerging multimodality. Evaluation remains overlap-heavy (EM/F1), with increasing use of retrieval diagnostics (e.g., Recall@k, MRR@k), human judgements, and LLM-as-judge protocols. Efficiency and security (poisoning, leakage, jailbreaks) are growing concerns. Discussion: Evidence supports a shift to modular, policy-driven RAG, combining hybrid/structure-aware retrieval, uncertainty-aware control, memory, and multimodality, to improve grounding and efficiency. To advance from prototypes to dependable systems, we recommend: (i) holistic benchmarks pairing quality with cost/latency and safety, (ii) budget-aware retrieval/tool-use policies, and (iii) provenance-aware pipelines that expose uncertainty and deliver traceable evidence. We note the evidence base may be affected by citation-lag from the inclusion thresholds and by English-only, five-library coverage. Funding: Advanced Research and Engineering Centre. Registration: Not registered. Full article
(This article belongs to the Special Issue Artificial Intelligence (AI) and Natural Language Processing (NLP))
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-8
Back to TopTop