International Journal of Information and Communication Technology (11 papers in press)

Regular Issues

• Open Access

  Application research of a LightGBM-based predictive evaluation model for college English learning behaviour ( Free Full-text Access )

  by Xinxin Yang 
  Abstract: In order to meet the demand for the digital modelling and intelligent analysis of students learning behaviour, a predictive evaluation framework is proposed, which combines feature engineering with LightGBM. Through the construction of tags and the extraction of training samples from college English course behaviour log, the construction strategy and interpretable output mechanism of the model are discussed. The results show that the proposed model achieves an F1-score of 0.889 on the test set, with an average response latency of less than 230 ms, and a performance fluctuation of less than 1.6% in 5 times cross validation, demonstrating robust deployment stability and generalisation.
  Keywords: learning behaviour prediction; LightGBM algorithm; educational data mining; Intelligent teaching analytics; learning behaviour modelling.
  DOI: 10.1504/IJICT.2027.10080149
   
  

• Open Access

  Comprehensive evaluation of key indexes of power engineering based on K-nearest neighbour algorithm ( Free Full-text Access )

  by Yulong Li, Wei Ni, Bo Chen 
  Abstract: To improve the accuracy of key indicator evaluation in power engineering, this study proposes a comprehensive evaluation method based on K-nearest neighbour (KNN) algorithm. Aiming at the limitations of traditional methods in processing nonlinear and high-dimensional data, an evaluation system including ten key indicators such as engineering cost, construction period, and equipment performance was constructed to conduct experiments on 50 power engineering project data in a certain region. The results show that compared with traditional methods, the KNN model has a 15% improvement in evaluation accuracy, a more reasonable allocation of indicator weights, and can effectively identify key factors affecting engineering quality and efficiency. It also exhibits strong robustness in dealing with nonlinear problems and is suitable for power engineering of different scales and types. This method provides a scientific basis for decision-making in power engineering and has promotional value.
  Keywords: KNN algorithm; power engineering; index analysis; comprehensive evaluation.
  DOI: 10.1504/IJICT.2026.10080314
   
  
• An international communication influence model for intangible cultural heritage using graph transformers and MoE architecture
  by Jing Zeng 
  Abstract: International dissemination of intangible cultural heritage (ICH) is difficult to assess because relevant data are heterogeneous, relational, and dynamically evolving. We propose GT-MoE-NIA, an influence assessment model that combines a graph transformer with a mixture-of-experts (MoE) architecture. A heterogeneous graph represents ICH projects, countries or regions, media, audiences, and their interactions. The graph transformer captures global structural and semantic dependencies, while a gating network dynamically routes representations to specialised experts for influence prediction. We evaluate the model on the Global Non-Material Cultural Heritage Propagation Dataset (GNCPD), integrating UNESCO inventories, GDELT news, Twitter data, and Wikipedia page views. Compared with GCN, GAT, and GraphSAGE baselines, GT-MoE-NIA reduces root mean square error by 18.7% and improves NDCG@10 by 22.4%. Expert-activation patterns also provide interpretable evidence of how dissemination modes affect influence, supporting data-driven resource allocation for international cultural promotion.
  Keywords: intangible cultural heritage; ICH; international dissemination; influence model; graph transformer; mixture of experts; heterogeneous graph neural network.
  This article is being considered for Open Access
   
  

• Open Access

  An NLP-based large-scale information extraction framework for modelling responsibility relations in judicial web documents ( Free Full-text Access )

  by Shuai Li 
  Abstract: The rapid advancement of ICT and intelligent judicial systems drives a digital transformation in the legal sector. Daily, massive volumes of unstructured judicial documents are generated. Converting these into machine-readable formats is essential for large-scale case retrieval and intelligent judgement prediction. However, legal texts feature complex sentence structures and implicit logical relationships. Traditional NLP techniques struggle with complex liability relationships due to severe long-tail data distributions and cascading errors. To overcome these bottlenecks, this paper proposes a large-scale NLP information extraction framework. It establishes a comprehensive classification system for responsibility relationships based on civil law. A document-level encoder combining Lawformer and BiGRU, integrated with dual self-distillation and label distribution-sensitive margin loss, mitigates classification bias. Furthermore, a joint entity and relationship extraction network (CJE-PCHF) alongside LLMs for prompt-based learning injects legal knowledge. Extensive experiments on datasets like LexRel and CAIL2018 demonstrate the framework substantially outperforms baseline models.
  Keywords: information and communication technology; ICT; natural language processing; NLP; information extraction; document-level relationship extraction; DLRE; deep learning; security architecture; liability relationship modelling.
  DOI: 10.1504/IJICT.2026.10081429
   
  

• Open Access

  A knowledge modelling framework for the preservation and transfer of intangible cultural heritage handicraft knowledge: the case of Yixing Zisha Pottery ( Free Full-text Access )

  by Qianhui Li, Pin Lv, Ge Huang 
  Abstract: Intangible cultural heritage (ICH) handicrafts face transmission crises due to their reliance on vulnerable tacit knowledge. To overcome traditional digital protection limitations, this study proposes a systematic knowledge modelling and transfer framework (ZKMT) using Yixing Zisha pottery as an empirical case. We construct a knowledge ontology (ZKO) based on CIDOC CRM to transform manual experience into structured data. Integrating SECI theory, we design a knowledge transfer mechanism facilitating tacit knowledge explicitisation. Furthermore, we employ AIGC for innovative design under strict ontology constraints, validated via an AHP Delphi model. Experiments demonstrate the framework improves complex retrieval accuracy to 93.8% and learner knowledge retention by 71.5%, while ensuring cultural authenticity in modern product design. This study provides a scientific paradigm for the preservation, knowledge management, and sustainable development of ICH in the digital era.
  Keywords: intangible cultural heritage; ICH; Yixing purple clay pottery; knowledge ontology; knowledge graph; SECI model; artificially generated content; AIGC; product design; knowledge transfer.
  DOI: 10.1504/IJICT.2026.10081471
   
  

• Open Access

  A comparative study of node influence ranking algorithms based on improved PageRank and betweenness centrality taking the Grand Canal cultural communication network as an example ( Free Full-text Access )

  by Lechi Wang 
  Abstract: Accurately identifying influential nodes in Grand Canal cultural dissemination networks is crucial for enhancing communication efficacy. Traditional betweenness centrality and standard PageRank exhibit severe limitations in multi-path, semantically rich, and time-varying cultural networks. This study proposes an improved PageRank (IPR) algorithm integrating topic similarity, interaction frequency, and temporal decay weights. By constructing a synthetic Grand Canal cultural dissemination network and quantitatively evaluating it via the susceptible-infectious-recovered (SIR) model, simulation results demonstrate that betweenness centrality misidentifies 'false structural holes' lacking diffusion capability (achieving only 24.3% cascade coverage). Conversely, the proposed IPR algorithm breaks the uniform transition assumption, reaching 72.1% coverage scale in simulated information cascades. This research provides a quantitative, multi-dimensional framework for node influence ranking in complex cultural networks.
  Keywords: complex network; node influence; improved Pagerank algorithm; betweenness centrality; cultural dissemination; Grand Canal; SIR Model.
  DOI: 10.1504/IJICT.2026.10081599
   
  

• Open Access

  Controllable diffusion-based AIGC for art design: a latent space disentanglement framework ( Free Full-text Access )

  by Muhan Huang, Xinshuang Xu 
  Abstract: Traditional text-to-image diffusion models face counterfactual inconsistency due to highly entangled latent spaces, limiting fine-grained control over design attributes like content, style, and layout. To address this, we propose the semantic disentangled diffusion engine (SDDE) framework, requiring no global retraining. By introducing dynamic Gaussian anchoring and latent alignment consistency regularisation, SDDE establishes clear causal decision boundaries. It combines with the Hessian score distillation sampling (HSDS) algorithm to orthogonally decompose the entangled latent space into independent semantic subspaces. A typography-aware feature splitter is also designed to suppress style leakage in mixed layouts. Extensive experiments on LICA and GraphicDesignBench demonstrate SDDE achieves a 95.6% semantic consistency score (SCS) and 85.9% layout and typography effectiveness (LTV), outperforming existing baselines in image quality. SDDE provides a solid foundation for zero-shot, causally consistent controllable intelligent assisted design.
  Keywords: artificial intelligence generated content; AIGC; text-to-image generation; diffusion models; latent space disentanglement; controllable generation; artistic design; feature orthogonalisation.
  DOI: 10.1504/IJICT.2026.10081600
   
  

• Open Access

  A hybrid data-driven framework for linking teacher professional development and organisational innovation capabilities ( Free Full-text Access )

  by Yanjun Liu, Wan Suraya Wan Nik, Jing Tang 
  Abstract: Teacher development is a crucial catalyst for organisational learning and innovation in education; however, conventional training models are disjointed and lack measurable links to innovation outcomes. This study proposes a hybrid data-driven fuzzy ensemble learning and structural framework (HD-FELS) to establish a predictive relationship between teacher professional growth and institutional innovation capacity. The framework combines random forest for ranking features, LSTM for recognising patterns over time, and fuzzy AHP for giving innovation indicators weights. Structural equation modelling checks for hidden relationships, and K-means clustering groups teachers based on how ready they are to learn. The results show that the intensity of professional development has a big effect on the ability to innovate. The proposed model is 11.3% more accurate than baseline models, with an accuracy rate of 94.7%. High-development cohorts show a 38.2% improvement in innovation capacity compared to low-development groups, highlighting the effectiveness of structured, data-driven professional growth strategies.
  Keywords: professional development; innovation capability; ensemble learning; fuzzy analytic hierarchy process; structural equation modelling; SEM; predictive analytics.
  DOI: 10.1504/IJICT.2026.10081601
   
  

• Open Access

  Personalising physical education courses via predictive analytics to improve student engagement and health outcomes ( Free Full-text Access )

  by Can Li 
  Abstract: Traditional physical education (PE) often adopts a one-size-fits-all approach, limiting student engagement (SE) and health outcomes. This study proposes a dynamic roach infestation-driven weighted random forest (DRI-WeightedRF) model that integrates swarm intelligence into ensemble learning to predict SE and health outcomes. In DRI-WeightedRF, cockroach-inspired exploration behaviours dynamically optimise feature weights and decision-tree importance: engagement-seeking, wellness motivation, vigilance, and collaborative peer learning guide adaptive weighting to capture complex physiological-psychological interactions. Unlike conventional optimisation-based Random Forest methods that statically tune hyperparameters, DRI-WeightedRF continuously refines feature relevance and tree contributions, enhancing predictive accuracy. Evaluated on a dataset of 5,000 collegiate athletes, DRI-WeightedRF achieved an accuracy of 98.50% with RMSE 0.0863, MSE 0.0074, and MAE 0.0421, outperforming existing models. The results demonstrate the models efficacy in personalising PE interventions to improve engagement and wellness.
  Keywords: physical education; student engagement; health outcomes; dynamic roach infestation-driven weighted random forest; DRI-WeightedRF.
  DOI: 10.1504/IJICT.2026.10081602
   
  

• Open Access

  A deep reinforcement learning model for dynamic generation of ideological and political teaching content ( Free Full-text Access )

  by Xiangqin Zhou 
  Abstract: To address the misalignment of static pre-designed teaching content with learners dynamic needs in ideological and political education, this paper proposes a dynamic content generation model based on deep reinforcement learning. The model formulates the sequential decision-making process of generating teaching content as a Markov decision process and designs a dual-encoder deep q-network algorithm. By integrating a gating mechanism with dual encoders for content semantics and pedagogical suitability, along with knowledge graph constraints, the model achieves real-time optimisation and value-oriented control of content sequences. Experiments on public datasets show that compared to standard deep q-network and collaborative filtering baselines, the proposed model improves content matching accuracy to 76.3% (an 8.0-percentage-point improvement over the standard deep Q-network) and cumulative training reward to 78.5 (a 10.3% relative improvement over proximal policy optimisation), validating its dynamic adaptation strategy.
  Keywords: deep reinforcement learning; ideological and political education; teaching content generation; deep Q-network; DQN.
  DOI: 10.1504/IJICT.2026.10081619
   
  

• Open Access

  Dynamic perception of ideological and political identity in classroom settings via multimodal self-supervised representation learning ( Free Full-text Access )

  by Fei Wang 
  Abstract: Ideological and political identity is a dynamic process continuously constructed in classroom teaching, whose perception faces three challenges: heterogeneous modalities are difficult to align, annotated samples are scarce, and signals fluctuate. This paper proposes a dynamic perception method for ideological and political identity based on multimodal self-supervised representation. The method designs two pre-training tasks: temporal consistency prediction and mask reconstruction, to learn high-discriminative representations under unlabeled conditions; it achieves unified heterogeneous modality space through progressive semantic alignment, introduces confidence gate adaptive adjustment to fusion weights to cope with signal fluctuations, and adopts gated recurrent units to model the temporal accumulation effect of identity, outputting the three-dimensional intensity of cognition, emotion, and behaviour. Experimental results show that the proposed method achieves an accuracy of 92.1% and a macro average F1 of 91.9%, which is significantly better than four baseline methods, verifying its effectiveness in classroom emotion perception tasks.
  Keywords: ideological and political identity perception; multimodal fusion; self-supervised representation; semantic alignment; gated recurrent unit.
  DOI: 10.1504/IJICT.2026.10081620