Search Results (90)

Sentiment analysis has become increasingly important across various domains, particularly in business intelligence, where it is crucial for improving the performance of companies by identifying the sentiments and emotions expressed in customer feedback on products and services. Despite its growing relevance, sentiment analysis still faces several challenges, including class imbalance in datasets, limitations in feature extraction techniques, and the selection of appropriate classification models. Effectively addressing these challenges requires the integration of robust representation methods, reliable data balancing strategies, and efficient classification frameworks. In this study, we propose a novel sentiment analysis approach that combines SBERT for contextual feature extraction, WGAN-based synthetic data generation for addressing class imbalance, and a soft voting ensemble classifier for improved prediction. The proposed approach is evaluated on five datasets, including two English datasets and three Arabic datasets, in order to assess its performance in a multilingual setting. We compare the effectiveness of the proposed model with several baseline machine learning classifiers, as well as with commonly used data balancing techniques such as the synthetic minority over-sampling technique (SMOTE) and adaptive synthetic (ADASYN). The evaluation is conducted using multiple performance metrics, including accuracy, precision, recall, F1-score, MCC, ROC–AUC and training and inference time, along with different validation strategies including fixed train–test splits and k-fold cross-validation. The experimental results demonstrate the effectiveness and stability of the proposed approach. In particular, they highlight the importance of capturing sentence-level contextual representations and generating realistic synthetic samples to address class imbalance. Full article

Background: Accurate three-dimensional positioning of dental implants is critical for ensuring biomechanical stability, prosthetic passivity, and long-term clinical success. While computer-assisted navigation systems achieve high precision, their complexity and cost often limit accessibility. This study presents the development and preclinical experimental validation of a low-cost prototype designed to enhance angular accuracy in dental implant placement within a controlled 3D haptic simulation environment. Methods: A preclinical experimental design was implemented using a 3D haptic simulator (Virteasy, Montpellier, France). The prototype incorporated high-precision inertial measurement units (IMUs) and an Extended Kalman Filter (EKF) for real-time angular feedback. Ninety-seven simulated implant placements were performed—both freehand and with prototype assistance—under identical virtual conditions by a single experienced operator. Angular deviations in mesiodistal and buccolingual planes were recorded, combined into a composite 3D index, and analyzed using paired t-tests and linear mixed-effects models. The study was conducted in a controlled simulation environment, which does not fully replicate clinical conditions. Results: The prototype significantly reduced angular deviation from 13.49° to 2.99° in the mesiodistal plane (−77.8%) and from 13.56° to 5.59° in the buccolingual plane (−58.8%), achieving an overall 67% improvement in three-dimensional orientation (p < 0.001; Cohen’s d = 1.47). Agreement with an optical reference system (OptiTrack) was excellent (bias = +0.36°, RMSE = 0.39°). Intra-operator reliability exceeded 0.95 (ICC), confirming strong reproducibility and measurement stability. Conclusions: The proposed inertial sensor-based prototype achieved angular accuracy within the range reported for computer-guided systems while maintaining advantages of portability, low cost, and usability. Its integration into haptic simulators provides a valid tool for both educational and preclinical applications, offering real-time feedback that enhances spatial perception and psychomotor learning. Future clinical studies should validate its performance in cadaveric and patient-based contexts to determine its practical impact on surgical precision and implant success. Full article

Previous evidence has identified the ventromedial prefrontal cortex (vmPFC) as crucial for implementing high-level semantic memory structures (schemas) during event construction. If this is the case, one would expect reduced semantic coherence in events mentally constructed by vmPFC patients compared to healthy and brain-damaged controls. We tested this prediction by having participants mentally construct events using objects as cues and reanalyzing a published dataset using sentences as cues. In both cases, we measured the semantic coherence of patients’ mental constructions and their semantic coherence with the cue, using transformer-based sentence embeddings (S-BERT), and further corroborated the findings with E5 Multilingual and E5 Italian embedding models. Our results reveal that the hypothesized impairment in semantic coherence following vmPFC damage is, in fact, task-dependent. With minimal (object) cues, vmPFC patients’ reports exhibited reduced local coherence, increased connectedness to the cues, and reduced lexical diversity. In contrast, with extended (sentence) cues, they showed preserved- or even enhanced-local and global coherence. We suggest that vmPFC integrity is necessary to trigger schema activation under minimal cue conditions. Although extended cues may facilitate schema activation, schemas are degraded and essentialized following vmPFC damage, thereby constraining patients’ mental constructions within a narrower—hence overly coherent—semantic space. Full article

Here, we propose a composite system that uses text summarization (TS) and question answering (QA) to supplement the IR process of long documents. Most previous studies have used separate approaches, i.e., either TS or QA. The aim of this paper is to develop an interaction between TS and QA in three stages to enhance IR performance. First, SBERT is used for summarization. Second, an RAG method is employed to retrieve information and generate answers. In the architecture of RAG, retrieval of the document is fulfilled via all-MiniLM-L6-v2, while answer generation is performed via the T5 and BART-large-cnn models. Third, the retrieved answers are assessed and compared with a baseline system in which the documents are treated without summarization. The proposed system aims to improve the quality of retrieved information and accuracy of answers generated by TSQA in a unified pipeline. Experimental evaluation conducted on the NIPS dataset demonstrates that the proposed approach significantly enhances summary informativeness and answer accuracy compared with traditional single-task approaches. The simulation results show improvements of 20.83% in text similarity and 2.38% in BERT scores for answer generation compared with the standard RAG baseline without summarization. Full article

Artificial intelligence has attracted increasing attention in the construction industry; however, automated time scheduling remains limited in practical applications. Schedule development remains manual, requiring planners to analyze project documents, define activities, estimate durations, and identify relationships based on logical sequence. This process primarily depends on individual experience and skills, making it both time-consuming and prone to human error. From an engineering design perspective, delayed or inconsistent schedule development weakens design-to-construction feedback, limiting the ability to evaluate constructability and time implications of alternative design decisions during early-stage planning. This study proposes an integrated BIM–Natural Language Processing (NLP) framework to automate activity identification, duration estimation, and logical sequencing for construction scheduling. The framework extracts project data from Revit, organizes it into a bill of quantities format, and then generates an activity list, each activity with a unique ID. Using Sentence-BERT (SBERT) embeddings, the framework estimates activity durations based on semantic similarity. The same semantic process is combined with rule-based reasoning to identify logical relationships, including sequences, supported by an Excel-based reference dictionary that includes logical relationships, productivity, and ID structure. Finally, the framework incorporates a crashing module that proportionally adjusts the duration of activities on the longest path to target the project’s completion time without violating relationships. The proposed framework was validated using real construction project data and produced reliable results. By producing a tool-ready schedule directly from design-model information, the proposed workflow enables earlier schedule feedback loops and supports design-informed planning by allowing designers and planners to assess the time consequences of model-driven scope changes. The results demonstrate that integrating BIM and NLP can transform conventional schedules into faster, more consistent processes, thereby supporting the construction industry. Full article

Construction safety texts are commonly used only for descriptive statistical analysis, and systematic approaches for uncovering latent semantic risk correlations remain limited. In particular, risk identification and prioritization under unlabeled conditions remain challenging. To address this issue, this study proposes a semantic risk association and ranking framework based on Sentence-BERT (SBERT). First, a domain-specific keyword library is constructed, and representative risk terms are extracted through tokenization, stop-word removal, and TF-IDF weighting. A fine-tuned SBERT model is then employed to generate sentence embeddings. FAISS-based similarity search is applied to match safety inspection records with historical accident reports, enabling automatic identification and ranking of the most relevant accident types. In addition, a seven-day inspection window is introduced to capture the temporal accumulation effect of hazards and support risk assessment without explicit labels. Experiments conducted on 1368 accident reports and 484 inspection records show that the proposed framework achieves an accuracy of 0.75, a recall of 1.00, and an F1-score of 0.8571. Cross-project validation yields an F1-score of 0.5607, and the performance remains stable under 10% noise interference. The results demonstrate that the proposed semantic risk association and ranking framework is effective and robust for practical construction safety management. Full article

To minimize cybersecurity risks in weapon systems, the implementation of the Korean Risk Management Framework (K-RMF) has become imperative. However, a significant “strategic gap” exists between high-level RMF controls and technical MITRE ATT&CK techniques, rendering manual mapping labor-intensive. This study proposes an automated mitigation-driven pipeline that integrates Sentence-BERT (SBERT) with the structural defense relationships of the ATT&CK knowledge graph. To address the data coverage limitations of the Center for Threat-Informed Defense (CTID) silver standard, we introduce Recall@restricted as a calibrated performance metric. Experimental evaluations demonstrate that the proposed ensemble framework achieves a Recall@restricted of 0.74, significantly outperforming baseline SBERT-only models. These findings suggest that deterministic mitigation relationships effectively complement semantic representations, providing a robust framework for aligning RMF controls with adversarial behaviors. Full article

Driven by the global rise in animal protein demand, poultry farming has evolved into a highly intensive and technically complex sector. According to the FAO, animal protein production increased by about 16% in the past decade, with poultry alone expanding by 27% and becoming the leading source of animal protein. This intensification requires rapid, complex decisions across multiple aspects of production under uncertainty and strict time constraints. This study presents the development and evaluation of a conversational decision support system (DSS) designed to support decision-making to assist poultry producers, particularly broiler producers, in addressing technical queries across five key domains: environmental control, nutrition, health, husbandry, and animal welfare. As a proof-of-concept study, the reference context is intensive broiler production, covering common floor-rearing housing settings, including environmentally controlled and mechanically ventilated houses. The system combines a large language model (LLM) with retrieval-based generation (RAG) to ground responses in a curated corpus of scientific and technical literature. Additionally, it adds a reasoning component using Paraconsistent Annotated Evidential Logic Eτ, a non-classical logic designed to handle contradictory or incomplete information. Methodologically, Logic Eτ is used as a workflow-level control mechanism to gate clarification, domain routing, and answer adequacy signaling, rather than serving only as a post hoc label on generated outputs. Evaluation was conducted by comparing system responses with expert reference answers using semantic similarity (cosine similarity with SBERT embeddings). The results indicate that the system successfully retrieves and composes relevant content, while the paraconsistent inference layer makes results easier to interpret and more reliable in the presence of conflicting or insufficient evidence. These findings suggest that the proposed architecture provides a viable foundation for explainable and reliable decision support in modern poultry production, achieving consistent reasoning under contradictory or incomplete information where conventional RAG chatbots may produce unstable guidance. Full article

The proliferation of generative artificial intelligence (AI) as an autonomous recommendation agent fundamentally challenges traditional paradigms of marketing communication. As AI systems increasingly mediate consumer–brand relationships, understanding how artificial agents construct persuasive discourse—distinct from human communicators—becomes critical for developing effective dual-channel marketing strategies. Grounded in Source Credibility Theory and the Computers Are Social Actors (CASA) paradigm, this study investigates the semantic and structural divergence between AI-generated product recommendations and human influencer marketing messages in social commerce contexts. Employing a mixed-methods computational approach integrating term frequency analysis, TF-IDF weighting, Latent Dirichlet Allocation (LDA) topic modeling, and BERT-based contextualized semantic embedding analysis (KR-SBERT), we examined 330 Instagram influencer posts and 541 AI-generated responses concerning inner beauty enzyme products—a hybrid category combining functional health claims with hedonic beauty appeals—in the Korean social commerce market. AI-generated responses were collected through a systematically designed query protocol with empirically grounded prompts derived from actual consumer search behaviors, and analytical robustness was verified through sensitivity analyses across multiple parameter thresholds. Our findings reveal a fundamental divergence in persuasive architecture: human influencers construct experiential narratives exhibiting message characteristics typically associated with peripheral-route cues (sensory descriptions, emotional testimonials, social context), while AI recommendations employ systematic, evidence-based discourse exhibiting message characteristics typically associated with central-route argumentation (functional mechanisms, ingredient specifications, objective criteria). Topic modeling identified four distinct thematic clusters for each source type: human discourse centers on embodied experience and relational consumption, whereas AI discourse organizes around informational utility and rational decision support. Jensen–Shannon Divergence analysis (JSD = 0.213 bits) confirmed moderate distributional divergence, while chi-square testing (χ² = 847.23, p < 0.001) and Cramér’s V (0.312, indicating a medium-to-large effect) demonstrated statistically significant and substantively meaningful differences. These findings extend CASA theory by demonstrating that AI recommendation agents develop a characteristic “AI communication signature” distinguishable from human persuasion patterns. We propose an integrated Dual-Agent Persuasion Proposition—synthesizing CASA, ELM, and Source Credibility perspectives—suggesting that AI and human recommenders serve complementary functions across different stages of the consumer decision journey—a proposition whose predictions regarding sequential persuasive effectiveness and consumer processing routes await experimental validation. These findings carry implications for AI content strategy optimization, platform design, and emerging regulatory frameworks for AI-generated content labeling. Full article

To address the limitations of static and coarse-grained analysis in mining online tourism reviews, this study proposes a gated attention-based multi-model fusion framework for dynamic topic evolution and complaint-driven latent issue pattern mining. Using 300,000 reviews from Ctrip and Meituan, we fuse global semantics from Sentence-BERT with attention (SBERT-Attention), local features from Bidirectional Encoder Representations from Transformers–Text Convolutional Neural Network (BERT-TextCNN), and topic distributions from the Biterm Topic Model (BTM) via a learnable gating mechanism. The fused model achieves an F1-score of 92.3% in review classification. We partition the corpus quarterly and apply Uniform Manifold Approximation and Projection (UMAP) followed by K-means++ clustering to the fused vectors, yielding interpretable topics, including Scenery, Transportation, Amenities, Management, Culture, and Value for Money, and enabling dynamic topic discovery over time. River map visualizations and negative review analysis reveal seasonal evolution patterns and recurring complaint patterns associated with specific topics. The framework enables dynamic, interpretable semantic mining, advancing intelligent processing of short-text user content and offering a generalizable approach for temporal knowledge discovery in smart tourism and beyond. Full article

Why do certain frames gain prominence while others become marginalized in public discourse about emerging technologies? Existing research shows that policy adoption serves as a powerful discursive signal that shapes how issues are interpreted. Yet prior work generally assumes that these framing effects unfold uniformly across jurisdictions. This paper argues instead that the discursive impact of policy adoption is contingent on the interjurisdictional landscape. Integrating insights from policy diffusion theory, I propose that interstate competitive pressure conditions how strongly policy adoption reshapes public discourse. To evaluate this argument, I analyze how autonomous vehicle (AV) policy adoption influences local media framing across U.S. states from 2012 to 2022. Using a dataset of 13,171 news articles, I classify economic, technological, and social/ethical frames with Sentence-BERT, a state-of-the-art semantic model, and estimate causal effects using a staggered difference-in-differences design. The results reveal stark contextual variation: in high-competition states, policy adoption increases economic framing while reducing social and ethical framing, whereas technological framing remains largely unchanged; by contrast, low-competition states exhibit minimal shifts across all frame types. These findings show that the framing effects of policy adoption are relational and context-dependent, advancing research on policy feedback, diffusion, and the politics of emerging technologies. Full article

Under the Belt and Road Initiative, whether architectural education effectively supports sustainability-oriented overseas practice remains insufficiently evidenced. Anchored in the Royal Institute of British Architects (RIBA) and the National Architectural Accrediting Board (NAAB) competency frameworks, this study constructs a tripartite analytical framework linking international standards, educational curricula, and overseas job requirements. Based on curriculum texts and 200 overseas job postings from major international recruitment platforms, paragraph-level semantic alignment is quantified using TF-IDF weighting, SBERT-based embeddings, cosine similarity, and clustering analysis. The results indicate a clear structural divergence: while domestic architectural education shows moderate alignment with overseas demand in foundational technical competencies (average similarity 0.58–0.62), it consistently underperforms in sustainability-critical dimensions—including BIM-based collaboration, international standard adaptation, cross-cultural coordination, and professional ethics—with similarity values below 0.45. This misalignment reflects a systemic imbalance between design-centered training and the governance-oriented competency structure required for sustainable overseas projects, providing a quantitative diagnostic basis for reconfiguring sustainability-oriented architectural education. Full article

In this research, the alignment and mapping between Modular Object-Oriented Dynamic Learning Environment (Moodle) learning resources and course topics are described using text similarity methods. The goal of this work is to improve the accuracy of automated alignment between Moodle course learning resources and course topics by analyzing text similarity method performance and examining factors that affect how closely they match expert evaluation. During this research, an expert first mapped the e-course learning resources to course topics, after which multiple text similarity techniques were applied to match resource titles and descriptions to those topics. The findings show that the Large Language Model (LLM)-based solution achieves the lowest mean absolute error (MAE), the lowest mean squared error (MSE), and the strongest agreement with expert evaluation. Traditional keyword-based methods, such as Jaccard similarity and Term Frequency–Inverse Document Frequency (TF-IDF), demonstrate moderate performance, while the Sentence Bidirectional Encoder Representations from Transformers (SBERT)-based model shows the weakest alignment with expert evaluation. Full article

Background: Haptic virtual simulation (HVS) has emerged as a promising tool in dental education, yet evidence comparing its performance to conventional preclinical training remains limited. Establishing its effectiveness is essential to support its integration into competency-based curricula. Objective: The aim of this study was to compare Class V cavity preparations performed using conventional training on extracted teeth with those performed using a haptic virtual simulator, evaluating preparation time and cavity volume. Methods: Sixty-one extracted human molars were digitized using cone-beam computed tomography (CBCT) to generate corresponding virtual replicas. A calibrated operator prepared 122 standardized Class V cavities (61 real and 61 virtual). The simulator automatically recorded preparation time and cavity volume. For natural teeth, cavity volume was calculated by digital superimposition of pre- and post-operative STL models using Blender. Paired means were compared using Student’s t-test (α = 0.05). Results: Preparation time was significantly shorter when using HVS compared with the conventional method (p < 0.001). Virtual preparations resulted in slightly larger cavity volumes than real preparations, with a statistically significant yet clinically small difference (p = 0.047). Conclusions: Haptic virtual simulation enables more time-efficient Class V cavity preparation while producing cavity volumes comparable to those obtained through conventional training. These findings support the implementation of haptic simulators as a valid and effective complement for preclinical skill acquisition in operative dentistry. Full article

This paper presents a scalable machine learning pipeline for extracting actionable, product-related insights from user-generated social media comments. Leveraging sentence embeddings from SBERT and unsupervised clustering (k-Means and agglomerative), the approach structures informal and noisy comments from Instagram and YouTube into topic groups intended to support thematic analysis. A case study on feedback regarding BMW vehicles, comprising more than 26,000 comments, illustrates how the pipeline can reveal recurring user concerns, such as design critiques, usability issues, and technology-related expectations, even in short and unstructured social media comments. The proposed pipeline operates without labeled data or manual annotation, enabling scalable application and transferability across product categories and industries. By transforming large-scale, unstructured consumer feedback into interpretable themes, the pipeline provides product teams with an efficient and structured basis for data-driven product development and improvement. Full article