Models Of Language Processing Research Articles

Text classification for evaluating digital technology adoption maturity based on BERT: An evidence of Industrial AI from China

Natural language processing (NLP) models, such as GPT and BERT, are predictable to subvert the research paradigm of technology foresight and innovation management, for their good objectivity, robustness, and efficiency. This paper aims to apply an NLP model based on deep learning to realize the digital technology adoption maturity evaluation. Firstly, a 3-layer evaluation system, with a hierarchy of domain-indicator-level, is proposed. Meanwhile, a dataset on the deployment of Industrial AI in China is collected and provided to our evaluation system. After data annotation by experts with reference to domains and indicators, a BERT model is introduced to execute the multi-label text classification task. The experiment results prove that our high-performance BERT model has the ability to learn from human experts, and then benefits to mitigate biases and reduce cost in evaluation. In the area of Industrial AI deployments, our research points out the digital technologies adoption maturity trends over time, trickle-down effect across regions, and the flying geese pattern between industries.

Morphologically-analyzed and syntactically-annotated Quran dataset.

This paper introduces the Morphologically-Analyzed and Syntactically-Annotated Quran (MASAQ) dataset, a comprehensive resource designed to address the scarcity of annotated Quranic Arabic corpora and facilitate the development of advanced Natural Language Processing (NLP) models. The Quran, being a cornerstone of classical Arabic, presents unique challenges for NLP due to its sacred nature and complex linguistic features. MASAQ provides a detailed syntactic and morphological annotation of the entire Quranic text, utilizing a rigorously verified text from Tanzil.net. The dataset includes more than 131K morphological entries and 123K instances of syntactic functions, covering a wide range of grammatical roles and relationships. The annotation process involved a team of expert Arabic linguists who employed traditional i'rab methodologies to ensure high accuracy and consistency. The dataset is structured in multiple formats (tab-separated text file (tsv), SQLite3 database (.db), comma-separated file (csv), and JavaScript Object Notation (.JSON)) to cater to various research needs. MASAQ's unique features include a comprehensive tagset of 72 syntactic roles, detailed morphological analysis, and context-specific annotations. This dataset is particularly valuable for tasks such as dependency parsing, grammar checking, machine translation, and text summarization. The potential applications of MASAQ are vast, ranging from pedagogical uses in teaching Arabic grammar to developing sophisticated NLP tools. By providing a high-quality, syntactically annotated dataset, MASAQ aims to advance the field of Arabic NLP, enabling more accurate and more efficient language processing tools. The dataset is made available under the Creative Commons Attribution 3.0 License, which governs its use and distribution. It has been created in compliance with ethical guidelines and with respect for the integrity of the Quranic text.

Discovering patient groups in sequential electronic healthcare data using unsupervised representation learning

IntroductionUnsupervised feature learning methods inspired by natural language processing (NLP) models are capable of constructing patient-specific features from longitudinal Electronic Health Records (EHR).DesignWe applied document embedding algorithms to real-world paediatric intensive care (PICU) EHR data to extract patient-specific features from 1853 patients’ PICU journeys using 647 unique lab tests and medication events. We evaluated the clinical utility of the patient features via a K-means clustering analysis.ResultsWe trained a document embedding model under a unique evaluation pipeline and obtained latent patient feature vectors for all 1853 patients. We performed unsupervised clustering to the patient vectors as a downstream analysis and obtained 5 distinct clusters via hyperparameter optimisation. Significant variations (p<0.0001) within both patient characteristics and surgery intervention and diagnostic profiles were detected.ConclusionThe K-means clustering results demonstrated the clinical utilities of the patient-specific features learned from the embedding algorithms. The latent patient features obtained via the embedding process enabled direct applications of other machine learning algorithms. Future work will focus on utilising the temporal information within EHR and extending EHR embedding algorithms to develop personalised patient journey predictions.

A phenotype-based AI pipeline outperforms human experts in differentially diagnosing rare diseases using EHRs

Rare diseases, affecting ~350 million people worldwide, pose significant challenges in clinical diagnosis due to the lack of experienced physicians and the complexity of differentiating between numerous rare diseases. To address these challenges, we introduce PhenoBrain, a fully automated artificial intelligence pipeline. PhenoBrain utilizes a BERT-based natural language processing model to extract phenotypes from clinical texts in EHRs and employs five new diagnostic models for differential diagnoses of rare diseases. The AI system was developed and evaluated on diverse, multi-country rare disease datasets, comprising 2271 cases with 431 rare diseases. In 1936 test cases, PhenoBrain achieved an average predicted top-3 recall of 0.513 and a top-10 recall of 0.654, surpassing 13 leading prediction methods. In a human-computer study with 75 cases, PhenoBrain exhibited exceptional performance with a top-3 recall of 0.613 and a top-10 recall of 0.813, surpassing the performance of 50 specialist physicians and large language models like ChatGPT and GPT-4. Combining PhenoBrain’s predictions with specialists increased the top-3 recall to 0.768, demonstrating its potential to enhance diagnostic accuracy in clinical workflows.

Automated extraction of post-stroke functional outcomes from unstructured electronic health records.

Population level tracking of post-stroke functional outcomes is critical to guide interventions that reduce the burden of stroke-related disability. However, functional outcomes are often missing or documented in unstructured notes. We developed a natural language processing (NLP) model that reads electronic health records (EHR) notes to automatically determine the modified Rankin Scale (mRS). We included consecutive patients (⩾18 years) with acute stroke admitted to our center (2015-2024). mRS scores were obtained from the Get With the Guidelines registry and clinical notes (if documented), and used as the gold standard to compare against NLP-generated scores. We used text-based features from notes, along with age, sex, discharge status, and outpatient follow-up to train a logistic regression for prediction of good (0-2) versus poor (3-6) mRS, and a linear regression for the full range of mRS scores. The models were trained for prediction of mRS at hospital discharge and post-discharge. The models were externally validated in a dataset of patients with brain injuries from a different healthcare center. We included 5307 patients, 5006 in train and test and 301 in validation; average age was 69 (SD 15) and 65 (SD 17) years, respectively; 47% female. The logistic regression achieved an area under the receiver operating curve (AUROC) of 0.94 [CI 0.93-0.95] (test) and 0.94 [0.91-0.96] (validation), and the linear model a root mean squared error (RMSE) of 0.91 [0.87-0.94] (test) and 1.17 [1.06-1.28] (validation). The NLP-based model is suitable for use in large-scale phenotyping of stroke functional outcomes and population health research.

SPIRIT-CONSORT-TM: a corpus for assessing transparency of clinical trial protocol and results publications.

Randomized controlled trials (RCTs) can produce valid estimates of the benefits and harms of therapeutic interventions. However, incomplete reporting can undermine the validity of their conclusions. Reporting guidelines, such as SPIRIT for protocols and CONSORT for results, have been developed to improve transparency in RCT publications. In this study, we report a corpus of 200 RCT publications, named SPIRIT-CONSORT-TM, annotated for transparency. We used a comprehensive data model that includes 83 items from SPIRIT and CONSORT checklists for annotation. Inter-annotator agreement was calculated for 30 pairs. The dataset includes 26,613 sentences annotated with checklist items and 4,231 terms. We also trained natural language processing (NLP) models that automatically identify these items in publications. The sentence classification model achieved 0.742 micro-F1 score (0.865 at the article level). The term extraction model yielded 0.545 and 0.663 micro-F1 score in strict and lenient evaluation, respectively. The corpus serves as a benchmark to train models that assist stakeholders of clinical research in maintaining high reporting standards and synthesizing information on study rigor and conduct.

Mapping the Green Urban: A Comprehensive Review of Materials and Learning Methods for Green Infrastructure Mapping.

Green infrastructure (GI) plays a crucial role in sustainable urban development, but effective mapping and analysis of such features requires a detailed understanding of the materials and state-of-the-art methods. This review presents the current landscape of green infrastructure mapping, focusing on the various sensors and image data, as well as the application of machine learning and deep learning techniques for classification or segmentation tasks. After finding articles with relevant keywords, the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyzes) method was used as a general workflow, but some parts were automated (e.g., screening) by using natural language processing and large language models. In total, this review analyzed 55 papers that included keywords related to GI mapping and provided materials and learning methods (i.e., machine or deep learning) essential for effective green infrastructure mapping. A shift towards deep learning methods can be observed in the mapping of GIs as 33 articles use various deep learning methods, while 22 articles use machine learning methods. In addition, this article presents a novel methodology for automated verification methods, demonstrating their potential effectiveness and highlighting areas for improvement.

Cultural Sensitivity in AI Language Learning: Using NLP to Enhance Language Understanding Across Cultural Contexts

The aim of this paper is to demonstrate the integration of cultural awareness into AI language learning systems using Natural Language Processing (NLP) models. Recognising that the traditional methods of language learning tend not to capture cultural variations, the studies focus on how culturally relevant NLP models (GPT-3, BERT, RNNs) promote language acquisition and cross-cultural integration. Data preprocessing, cultural data augmentation and model training was used to encode cultural variables such as greetings, politeness, and contextually relevant expressions into training datasets. Experimental results suggest that culturally sensitive models outperform the generic model on tasks that involve cultural awareness, such as politeness detection, cultural phrase recognition, and tone sensitivity. GPT-3 for example improved the accuracy of politeness detection tasks from 72.4% to 85.7%. These results highlight the need to bring cultural awareness into AI to develop engaging, context-sensitive language learning. It concludes that culturally based NLP models enhance learner capacity for real-world communication and foster global cultural awareness. Future work should focus on expanding culturally diverse datasets and refining AI models to address subtle cultural complexities

Natural Language Processing for Dialects of a Language: A Survey

State-of-the-art natural language processing (NLP) models are trained on massive training corpora, and report a superlative performance on evaluation datasets. This survey delves into an important attribute of these datasets: the dialect of a language. Motivated by the performance degradation of NLP models for dialectal datasets and its implications for the equity of language technologies, we survey past research in NLP for dialects in terms of datasets, and approaches. We describe a wide range of NLP tasks in terms of two categories: natural language understanding (NLU) (for tasks such as dialect classification, sentiment analysis, parsing, and NLU benchmarks) and natural language generation (NLG) (for summarisation, machine translation, and dialogue systems). The survey is also broad in its coverage of languages which include English, Arabic, German, among others. We observe that past work in NLP concerning dialects goes deeper than mere dialect classification, and extends to several NLU and NLG tasks. For these tasks, we describe classical machine learning using statistical models, along with the recent deep learning-based approaches based on pre-trained language models. We expect that this survey will be useful to NLP researchers interested in building equitable language technologies by rethinking LLM benchmarks and model architectures.

Using a machine learning framework for natural language processing to create a high-resolution carbon emission map for urban manufacturing

Managing carbon emissions from the manufacturing sector is crucial for sustainable development, and effective identification of manufacturing land is key to achieving this goal. However, current methods for identifying urban manufacturing land remain inadequate. In this study, we employ a fine-tuned, pre-trained natural language processing model based on Bidirectional Encoder Representations from Transformers to classify points of interest data into manufacturing industry categories. This approach enables us to identify manufacturing land and allocate corresponding carbon emissions data to specific parcels. The global Moran’s Index and local Moran’s Index are applied to analyze the relationship between manufacturing concentration and carbon emission intensity. The results demonstrate that the fine-tuned model achieved an accuracy rate of 91.6% on the test set, successfully identifying 98.72% of the manufacturing land in the study area. The intensity of carbon emissions from manufacturing exhibits a significant positive spatial correlation, with urban areas characterized by high-high and low-low clustering of emissions. In rural areas, high-emission manufacturers tend to be co-located with low-emission enterprises. Within individual manufacturing sectors, most exhibit low-low clustering, suggesting a potential relationship between such clustering and lower carbon emissions. This study provides detailed spatial data for the management of carbon emissions in the manufacturing sector and addresses the gap in micro-scale research on the correlation between manufacturing concentration and carbon emissions.

The role of chromatin state in intron retention: A case study in leveraging large scale deep learning models.

Complex deep learning models trained on very large datasets have become key enabling tools for current research in natural language processing and computer vision. By providing pre-trained models that can be fine-tuned for specific applications, they enable researchers to create accurate models with minimal effort and computational resources. Large scale genomics deep learning models come in two flavors: the first are large language models of DNA sequences trained in a self-supervised fashion, similar to the corresponding natural language models; the second are supervised learning models that leverage large scale genomics datasets from ENCODE and other sources. We argue that these models are the equivalent of foundation models in natural language processing in their utility, as they encode within them chromatin state in its different aspects, providing useful representations that allow quick deployment of accurate models of gene regulation. We demonstrate this premise by leveraging the recently created Sei model to develop simple, interpretable models of intron retention, and demonstrate their advantage over models based on the DNA language model DNABERT-2. Our work also demonstrates the impact of chromatin state on the regulation of intron retention. Using representations learned by Sei, our model is able to discover the involvement of transcription factors and chromatin marks in regulating intron retention, providing better accuracy than a recently published custom model developed for this purpose.

Fake News Detection and Classification: A Comparative Study of Convolutional Neural Networks, Large Language Models, and Natural Language Processing Models

In an era where fake news detection has become a pressing issue due to its profound impacts on public opinion, democracy, and social trust, accurately identifying and classifying false information is a critical challenge. In this study, the effectiveness is investigated of advanced machine learning models—convolutional neural networks (CNNs), bidirectional encoder representations from transformers (BERT), and generative pre-trained transformers (GPTs)—for robust fake news classification. Each model brings unique strengths to the task, from CNNs’ pattern recognition capabilities to BERT and GPTs’ contextual understanding in the embedding space. Our results demonstrate that the fine-tuned GPT-4 Omni models achieve 98.6% accuracy, significantly outperforming traditional models like CNNs, which achieved only 58.6%. Notably, the smaller GPT-4o mini model performed comparably to its larger counterpart, highlighting the cost-effectiveness of smaller models for specialized tasks. These findings emphasize the importance of fine-tuning large language models (LLMs) to optimize the performance for complex tasks such as fake news classifier development, where capturing subtle contextual relationships in text is crucial. However, challenges such as computational costs and suboptimal outcomes in zero-shot classification persist, particularly when distinguishing fake content from legitimate information. By highlighting the practical application of fine-tuned LLMs and exploring the potential of few-shot learning for fake news detection, this research provides valuable insights for news organizations seeking to implement scalable and accurate solutions. Ultimately, this work contributes to fostering transparency and integrity in journalism through innovative AI-driven methods for fake news classification and automated fake news classifier systems.

Text Categorization for Information Retrieval Using NLP Models

The paper presents the state-of-the-art natural language processing (NLP) models and methods, such as BERT and DistilBERT, to evaluate textual data and extract noteworthy insights. Preprocessing textual input, tokenization, and the implementation of deep learning architectures such as bidirectional LSTMs for classification tasks are all components of the approach that has been presented. To achieve the goal of producing accurate prediction models with the least amount of validation loss possible. Natural language processing (NLP) is a major focus of the manuscript in multiple areas such as sentiment analysis, language understanding, and text classification. The results show that our proposed NLP models perform exceptionally well. Long-term memory and natural language processing (NLP) go hand in hand. Therefore, these results demonstrate the value and relevance of our natural language processing approach to obtaining unstructured text data to improve and develop a variety of applications, such as chatbots, virtual assistants, and information retrieval systems, as well as to gain insights and help make better decisions, and the flexibility and generalizability of the models, while confirming their ability to handle a range of activities and textual materials. Excellent and accurate results were obtained in terms of validation, with the experimental models often exceeding the 99.85% accuracy benchmark. Another crucial factor to consider is that the average validation loss metrics for all tests remained remarkably low at 0.0058.

Schizophrenia more employable than depression? Language-based artificial intelligence model ratings for employability of psychiatric diagnoses and somatic and healthy controls.

Artificial Intelligence (AI) assists recruiting and job searching. Such systems can be biased against certain characteristics. This results in potential misrepresentations and consequent inequalities related to people with mental health disorders. Hence occupational and mental health bias in existing Natural Language Processing (NLP) models used in recruiting and job hunting must be assessed. We examined occupational bias against mental health disorders in NLP models through relationships between occupations, employability, and psychiatric diagnoses. We investigated Word2Vec and GloVe embedding algorithms through analogy questions and graphical representation of cosine similarities. Word2Vec embeddings exhibit minor bias against mental health disorders when asked analogies regarding employability attributes and no evidence of bias when asked analogies regarding high earning jobs. GloVe embeddings view common mental health disorders such as depression less healthy and less employable than severe mental health disorders and most physical health conditions. Overall, physical, and psychiatric disorders are seen as similarly healthy and employable. Both algorithms appear to be safe for use in downstream task without major repercussions. Further research is needed to confirm this. This project was funded by the London Interdisciplinary Social Science Doctoral Training Programme (LISS-DTP). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Why do consumers purchase energy-efficient kitchen appliance? An analysis based on online review comments.

Kitchen appliances constitute a significant portion of residential energy consumption. Promoting consumer purchases of high-energy-efficient kitchen appliances can effectively facilitate the transition to a low-carbon society. However, the role of energy saving in the current purchasing behavior of Chinese consumers regarding kitchen appliances remains unclear. Based on user-generated content from online e-commerce platforms (N=59,908), this study investigates whether Chinese consumers consider energy efficiency and its influencing factors when purchasing kitchen appliances through natural language processing and structural equation modeling techniques. The study findings reveal that: (1): Perceived energy saving is an important consideration for consumers to adopt kitchen appliances. (2): Prices benefits increase consumers' willingness to purchase energy-efficient appliances. (3): Consumers prioritize energy saving in the purchase of large kitchen appliances. (4): the effect of perceived energy saving on intention to purchase kitchen appliances is much stronger among high energy-efficient appliances. The results of this study propose specific policy recommendations to ensure the continuity of current demand-side energy efficiency policies related to kitchen appliances, utilize pricing mechanisms to incentivize consumers to purchase high-energy-efficient appliances, emphasize the importance of energy consumption of different types of kitchen appliance in environmental education, and establish stricter energy efficiency standards for kitchen appliances.

The Use of Natural Language Processing Model in Literary Style Analysis of Chinese Text

The Use of Natural Language Processing Model in Literary Style Analysis of Chinese Text

Widespread use of ChatGPT and other Artificial Intelligence tools among medical students in Uganda: A cross-sectional study.

Chat Generative Pre-trained Transformer (ChatGPT) is a 175-billion-parameter natural language processing model that uses deep learning algorithms trained on vast amounts of data to generate human-like texts such as essays. Consequently, it has introduced new challenges and threats to medical education. We assessed the use of ChatGPT and other AI tools among medical students in Uganda. We conducted a descriptive cross-sectional study among medical students at four public universities in Uganda from 1st November 2023 to 20th December 2023. Participants were recruited by stratified random sampling. We used a semi-structured questionnaire to collect data on participants' socio-demographics and use of AI tools such as ChatGPT. Our outcome variable was use of AI tools. Data were analyzed descriptively in Stata version 17.0. We conducted a modified Poisson regression to explore the association between use of AI tools and various exposures. A total of 564 students participated. Almost all (93%) had heard about AI tools and more than two-thirds (75.7%) had ever used AI tools. Regarding the AI tools used, majority (72.2%) had ever used ChatGPT, followed by SnapChat AI (14.9%), Bing AI (11.5%), and Bard AI (6.9%). Most students use AI tools to complete assignments (55.5%), preparing for tutorials (39.9%), preparing for exams (34.8%) and research writing (24.8%). Students also reported the use of AI tools for nonacademic purposes including emotional support, recreation, and spiritual growth. Older students were 31% less likely to use AI tools compared to younger ones (Adjusted Prevalence Ratio (aPR):0.69; 95% CI: [0.62, 0.76]). Students at Makerere University were 66% more likely to use AI tools compared to students in Gulu University (aPR:1.66; 95% CI:[1.64, 1.69]). The use of ChatGPT and other AI tools was widespread among medical students in Uganda. AI tools were used for both academic and non-academic purposes. Younger students were more likely to use AI tools compared to older students. There is a need to promote AI literacy in institutions to empower older students with essential skills for the digital age. Further, educators should assume students are using AI and adjust their way of teaching and setting exams to suit this new reality. Our research adds further evidence to existing voices calling for regulatory frameworks for AI in medical education.

NaturePred: A Tool for Revolutionizing Natural Product Classification with Artificial Intelligence

Background: The identification and classification of natural products are vital in drug discovery and bioactive compound exploration. Traditional methods are laborious and timeconsuming, necessitating innovative tools for accurate predictions using advanced AI techniques. Objectives: This paper presents NaturePred, a user-friendly tool designed to predict the class of natural products and calculate eight physicochemical properties of protein sequences. It aims to accurately predict five distinct classes of natural product biosynthetic gene clusters (BGCs): Polyketide Synthases (PKS), Non-ribosomal Peptide Synthetases (NRPS), Ribosomally Synthesized and Post- Translationally Modified Peptides (RiPPs), Terpenes, and PKS-NRPS Hybrids. It also addresses reliability in multi-class classification with a 90% confidence score threshold. Method: NaturePred offers three input options: single protein sequence, CSV file, or GenBank (.gbk) file. It uses a pipeline with a Natural Language Processing model based on TF-IDF (Term Frequency- Inverse Document Frequency) and a Logistic Regression classifier. Predictions are made if the confidence score exceeds 90%; otherwise, "None of the above class" is predicted. Evaluation with unseen data from the MiBIG database shows high accuracy (~96%) in assigning BGCs. Results: NaturePred provides accurate predictions with high confidence scores, demonstrating reliability across different datasets. It calculates eight physicochemical properties of protein sequences, offering valuable insights for further analysis. Conclusion: NaturePred's integrated features, including versatile input options, accurate predictions, and physicochemical property calculations, make it an indispensable tool in natural product research. By addressing classification challenges, NaturePred facilitates drug discovery and bioactive compound exploration, advancing the field. Tool available: (http://login1.cabgrid.res.in:5101/).

SOCIAL DETERMINANTS OF HEALTH ASSOCIATED WITH 30-DAY REHOSPITALIZATION BY USING DISCHARGE SUMMARIES

Abstract Background There has been increasing interest in the use of Social Determinants of Health (SDOH) in cardiovascular disease outcomes by reducing health disparities. For example, Centers for Medicare and Medicaid Services will require the hospitals reporting five SDOH components (housing, intimate partner violence, utilities, food insecurity and transportation insecurity) in 2025. There is limited evidence which SDOH components are associated with 30-day rehospitalization in HF patients who were in the ICU. Objective: To assess associations between the SDOH and 30-day rehospitalization in HF patients who were in the ICU by using the Medical Information Mart for Intensive Care III (MIMIC-III) data. Methods We identified HF patients by using ICD-9 codes related to HF from the MIMIC-III data that is de-identified and is publicly available. We used python to extract SDOH features from discharge summaries and used Chi-square statistical test (whether or not keyword is contained in discharge summaries vs whether or not HF patients have 30-day hospital rehospitalization). Results Mean age was 71 (± 14.2), 53% were male, and 73% were white. In particular, keyword “daughter” contributes to the 30-day rehospsitalization. It is unclear how daughter contributes 30-day rehospitalization but “daughter can be one of the SDOH components as social support. Conclusion It is difficult to identify how “daughter” is related to 30-day rehospitalization. We will utilize natural language processing models to analyzing the real-world social meaning of SDOH keywords to understand the correlation (e.g. the “daughter” reflecting patients have daughter accompany or other status).

ChatGPT 기능이 대학생의 학습성과와 학업성취도를 매개로 지속이용의도에 미치는 영향

With the change of the 4th Industrial Revolution era and the radical development of computing technology, the importance of software is increasing and software technology is being used in all industries throughout life. In addition, chatGPT, a GPT-based interactive artificial intelligence service developed by Open AI, is also showing rapid development. Based on a vast knowledge database, chatGPT provides sophisticated answers in a variety of knowledge areas. As chatGPT gradually develops, it is being used to perform tasks that require human intelligence, especially its impact on education is increasing. chatGPT, based on artificial intelligence (AI), is a natural language processing model that allows users to understand and solve programming concepts and problems in natural language, analyzes learners' questions and answers, and provides an optimized learning path to individual learners, thereby improving learning efficiency or learning outcomes. This paper focuses on the effect of chatGPT on college students' learning outcomes, achievements, and continuous use intention. Therefore, in this study, the concept of chatGPT and the user's intention to continue using it were clarified by classifying it into five functions: efficiency, convenience, problem-solving ability, usefulness, and interaction. In addition, in this study, two parameters, learning outcomes and academic achievement, were presented, and a corresponding research model was presented. Samples were collected using questionnaires and the hypothesis was verified by questionnaire analysis using SPSS 23.0 and Smart PLS 4.0. The following conclusions were drawn. First, H1 was partially accepted. Second, because the convenience of chatGPT did not have a positive effect on academic performance and academic achievement, H1-2 and H2-2 were rejected. chatGPT was adopted because its efficiency, usefulness, and interactivity had a significant impact on learning outcomes and academic achievement. Therefore, H2 is partially accepted. Third, because learning outcomes have a significant impact on the intention to continue using chatGPT, H3 was adopted. Fourth, because academic achievement had a significant effect on the intention to continue using chatGPT, H4 was adopted.