Search

Feedback is a crucial component of student learning. As advancements in technology have enabled the adoption of digital learning environments with assessment capabilities, the frequency, delivery format, and timeliness of feedback derived from educational assessments have also changed progressively. Advanced technologies powered by Artificial Intelligence (AI) enable teachers to generate different types of feedback supporting student learning. Despite the rapid uptake of digital technologies in education, previous studies on educational feedback primarily focused on the theoretical underpinnings of feedback practices, which are limited in terms of their coverage of AI-based technologies. This paper aims to inform both researchers and practitioners about the present and future of AI applications in feedback practices, identify and organize potential areas for the use of AI for feedback purposes, and establish venues for AI research and practice in educational feedback. Furthermore, the role of the three branches of AI (i.e., natural language processing, educational data mining, and learning analytics) in feedback practices and potential areas for their future development are discussed.

The massive amount of information from the internet has revolutionized the field of natural language processing. One of the challenges was estimating the similarity between texts. This has been an open research problem although various studies have proposed new methods over the years. This paper surveyed and traced the primary studies in the field of text similarity. The aim was to give a broad overview of existing issues, applications, and methods of text similarity research. This paper identified four issues and several applications of text similarity matching. It classified current studies based on intrinsic, extrinsic, and hybrid approaches. Then, we identified the methods and classified them into lexical-similarity, syntactic-similarity, semanticsimilarity, structural-similarity, and hybrid. Furthermore, this study also analyzed and discussed method improvement, current limitations, and open challenges on this topic for future research directions. As the results, this paper highlighted the importance of selecting the appropriate preprocessing algorithms to reduce data dimensionality and also combining several algorithms to enhance the overall matching and detection process. [ABSTRACT FROM AUTHOR]

During the artificial intelligence (AI) era, AI has evolved into a multidisciplinary industry in all domains. {NLP) Natural language processing, represents one of the most fascinating AI tasks. It can perform a number of tasks including question answering (QA), machine translation, entity linking, text generation, topic modelling, text summarization, and text to speech (TTS). The QA task is the focus of this research. It highlights the Open-Domain Question-Answering ODQA task explained using the field of Islamic religion. In this research, the QA task presents a model for developing an lslamBot QA system. lslamBot is a question-and-answer chatbot that is freeformed which can answer Islamic-related questions. The models of deep learning-based retrieval-reader were used to create the ODQA model. This paper uses a model that is based on data derived from the English Islamic Articles Database (EIAD). The EIAD dataset is a labelled ODQA dataset that was crowdsourced. The EIAD dataset contains approximately 1 Ok articles, 7 .5k of which were crowdsourced, and approximately 1 Ok question-answer pairs. Every article contains at least one question-and-answer pair. This paper develops an end-to-end ODQA model that uses the EIAD dataset to create a benchmark and an entirely novel baseline model. It also sets a new standard with the most recent Dense Passage Retriever models, which achieve 78% R@lOO. The ODQA model also generated novel results. It received a 71.5% EM and a 75.8% Fl score. Furthermore, due to the length of the answer, the use of the longform open-domain type is a hard issue: justification answer. Besides, the input of the model is only the question without context. [ABSTRACT FROM AUTHOR]

Biomedical-named entity recognition (bNER) is critical in biomedical informatics. It identifies biomedical entities with special meanings, such as people, places, and organizations, as predefined semantic types in electronic health records (EHR). bNER is essential for discovering novel knowledge using computational methods and Information Technology. Early bNER systems were configured manually to include domain-specific features and rules. However, these systems were limited in handling the complexity of the biomedical text. Recent advances in deep learning (DL) have led to the development of more powerful bNER systems. DL-based bNER systems can learn the patterns of biomedical text automatically, making them more robust and efficient than traditional rule-based systems. This paper reviews the healthcare domain of bNER, using DL techniques and artificial intelligence in clinical records, for mining treatment prediction. bNER-based tools are categorized systematically and represent the distribution of input, context, and tag (encoder/decoder). Furthermore, to create a labeled dataset for our machine learning sentiment analyzer to analyze the sentiment of a set of tweets, we used a manual coding approach and the multi-task learning method to bias the training signals with domain knowledge inductively. To conclude, we discuss the challenges facing bNER systems and future directions in the healthcare field. [ABSTRACT FROM AUTHOR]

With the development of cities and the prevalence of networks, interpersonal relationships have become increasingly distant. When people crave communication, they hope to find someone to confide in. With the rapid advancement of deep learning and big data technologies, an enabling environment has been established for the development of intelligent chatbot systems. By effectively combining cutting-edge technologies with human-centered design principles, chatbots hold the potential to revolutionize our lives and alleviate feelings of loneliness. A multi-topic chat companion robot based on a state machine has been proposed, which can engage in fluent dialogue with humans and meet different functional requirements. It can chat with users about movies, music, and other related topics, and recommend movies and music that may interest them to alleviate their loneliness and provide companionship. The interaction platform of the companion robot is realized through the QQ communication platform,with two chatmodes:Conversationmode and recommendationmode. First, the KdConv open-source corpus was selected, and Python was used to crawl information on movies and music from Douban and QQ Music to establish and pre-process the dataset. Then, the dialogue function was implemented using generative language models and retrieval systems, while the recommendation function was achieved using user profiling and collaborative filtering. Finally, a state machine algorithm was used to achieve real-time switching between the two chat modes of the companion robot. In conclusion, test participants gave high ratings for the accuracy of the companion robot's responses and the satisfaction with its content recommendations. Compared to traditional large-scale integrated models, this robot employs a state-machine framework to achieve diverse functions through seamless state transitions, thereby enhancing computational speed and precision. Additionally, the robot can recommend movies and music, providing companionship and alleviating loneliness for users, which is of great significance in modern society where interpersonal relationships are increasingly alienated. [ABSTRACT FROM AUTHOR]

With the recent advances in deep learning, different approaches to improving pre-trained language models (PLMs) have been proposed. PLMs have advanced state-of-the-art (SOTA) performance on various natural language processing (NLP) tasks such as machine translation, text classification, question answering, text summarization, information retrieval, recommendation systems, named entity recognition, etc. In this paper, we provide a comprehensive review of prior embedding models as well as current breakthroughs in the field of PLMs. Then, we analyse and contrast the various models and provide an analysis of the way they have been built (number of parameters, compression techniques, etc.). Finally, we discuss the major issues and future directions for each of the main points. [ABSTRACT FROM AUTHOR]

Artificial intelligence-based question-answering (QA) systems can expedite the performance of various tasks. These systems either read passages and answer questions given in natural languages or if a question is given, they extract the most accurate answer from documents retrieved from the internet. Arabic is spoken by Arabs and Muslims and is located in the middle of the Arab world, which encompasses the Middle East and North Africa. It is difficult to use natural language processing techniques to process modern Arabic owing to the language's complex morphology, orthographic ambiguity, regional variations in spoken Arabic, and limited linguistic and technological resources. Only a few Arabic QA experiments and systems have been designed on small datasets, some of which are yet to be made available. Although several reviews of Arabic QA studies have been conducted, the number of studies covered has been limited and recent trends have not been included. To the best of our knowledge, only two systematic reviews focused on Arabic QA have been published to date. One covered only 26 primary studies without considering recent techniques, while the other covered only nine studies conducted for Holy Qur'an QA systems. Here, the included studies were analyzed in terms of the datasets used, domains covered, types of Arabic questions asked, information retrieved, the mechanism used to extract answers, and the techniques used. Based on the results of the analysis, several limitations, concerns, and recommendations for future research were identified. Additionally, a novel taxonomy was developed to categorize the techniques used based on the domains and approaches of the QA system. [ABSTRACT FROM AUTHOR]

Efficient information search from building information models (BIMs) requires deep BIM knowledge or extensive engineering efforts for building natural language (NL)-based interfaces. To address this challenge, this paper introduces a dynamic prompt-based virtual assistant framework dubbed "BIMS-GPT" that integrates generative pre-trained transformer (GPT) technologies, supporting NL-based BIM search. To understand users' NL queries, extract relevant information from BIM databases, and deliver NL responses along with 3D visualizations, a dynamic prompt-based process was developed. In a case study, BIMS-GPT's functionality is demonstrated through a virtual assistant prototype for a hospital building. When evaluated with a BIM query dataset, the approach achieves accuracy rates of 99.5% for classifying NL queries with incorporating 2% of the data in prompts. This paper contributes to the advancement of effective and versatile virtual assistants for BIMs in the construction industry as it significantly enhances BIM accessibility while reducing the engineering and training data prerequisites for processing NL queries. • Introduced a dynamic prompt-based virtual assistant for BIM information search • Integrated BIM and GPT technologies for developing natural language interfaces • Explored prompt engineering for GPT to interpret NL queries and summarize NL answers • Improved BIM accessibility by enabling NL-based interactions with 3D visualizations • Reduced engineering and training data prerequisites for processing BIM NL queries [ABSTRACT FROM AUTHOR]

Document-oriented databases, a type of Not Only SQL (NoSQL) database, are gaining popularity owing to their flexibility in data handling and performance for large-scale data. MongoDB, a typical document-oriented database, is a database that stores data in the JSON format, where the upper field involves lower fields and fields with the same related parent. One feature of this document-oriented database is that data are dynamically stored in an arbitrary location without explicitly defining a schema in advance. This flexibility violates the above property and causes difficulties for application program readability and database maintenance. To address these issues, we propose a reconstruction support method for document structures in MongoDB. The method uses the strength of the Has-A relationship between the parent and child fields, as well as the similarity of field names in the MongoDB documents in natural language processing, to reconstruct the data structure in MongoDB. As a result, the method transforms the parent and child fields into more coherent data structures. We evaluated our methods using real-world data and demonstrated their effectiveness. [ABSTRACT FROM AUTHOR]

Existing natural language processing (NLP) methods to convert free-text clinical notes into structured data often require problem-specific annotations and model training. This study aims to evaluate ChatGPT's capacity to extract information from free-text medical notes efficiently and comprehensively. We developed a large language model (LLM)-based workflow, utilizing systems engineering methodology and spiral "prompt engineering" process, leveraging OpenAI's API for batch querying ChatGPT. We evaluated the effectiveness of this method using a dataset of more than 1000 lung cancer pathology reports and a dataset of 191 pediatric osteosarcoma pathology reports, comparing the ChatGPT-3.5 (gpt-3.5-turbo-16k) outputs with expert-curated structured data. ChatGPT-3.5 demonstrated the ability to extract pathological classifications with an overall accuracy of 89%, in lung cancer dataset, outperforming the performance of two traditional NLP methods. The performance is influenced by the design of the instructive prompt. Our case analysis shows that most misclassifications were due to the lack of highly specialized pathology terminology, and erroneous interpretation of TNM staging rules. Reproducibility shows the relatively stable performance of ChatGPT-3.5 over time. In pediatric osteosarcoma dataset, ChatGPT-3.5 accurately classified both grades and margin status with accuracy of 98.6% and 100% respectively. Our study shows the feasibility of using ChatGPT to process large volumes of clinical notes for structured information extraction without requiring extensive task-specific human annotation and model training. The results underscore the potential role of LLMs in transforming unstructured healthcare data into structured formats, thereby supporting research and aiding clinical decision-making. [ABSTRACT FROM AUTHOR]

Copyright of Arab International Journal of Library & Information is the property of Arab Institution of Knowledge Management and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Named entity recognition (NER) is a powerful computer system that utilizes various computing strategies to extract information from raw text input, since the early 1990s. With rapid advancement in AI and computing, NER models have gained significant attention and been serving as foundational tools across numerus professional domains to organize unstructured data for research and practical applications. This is particularly evident in the medical and healthcare fields, where NER models are essential in efficiently extract critical information from complex documents that are challenging for manual review. Despite its successes, NER present limitations in fully comprehending natural language nuances. However, the development of more advanced and user-friendly models promises to improve work experiences of professional users significantly. [ABSTRACT FROM AUTHOR]

OBJECTIVE: To compare the accuracy of an artificial intelligence chatbot to clinical practice guidelines (CPGs) recommendations for providing answers to complex clinical questions on lumbosacral radicular pain. DESIGN: Cross-sectional study. METHODS: We extracted recommendations from recent CPGs for diagnosing and treating lumbosacral radicular pain. Relative clinical questions were developed and queried to OpenAI's ChatGPT (GPT-3.5). We compared ChatGPT answers to CPGs recommendations by assessing the (1) internal consistency of ChatGPT answers by measuring the percentage of text wording similarity when a clinical question was posed 3 times, (2) reliability between 2 independent reviewers in grading ChatGPT answers, and (3) accuracy of ChatGPT answers compared to CPGs recommendations. Reliability was estimated using Fleiss' kappa (k) coefficients, and accuracy by interobserver agreement as the frequency of the agreements among all judgments. RESULTS: We tested 9 clinical questions. The internal consistency of text ChatGPT answers was unacceptable across all 3 trials in all clinical questions (mean percentage of 49%, standard deviation of 15). Intrareliability (reviewer 1: k = 0.90, standard error [SE] = 0.09; reviewer 2: k = 0.90, SE = 0.10) and interreliability (k = 0.85, SE = 0.15) between the 2 reviewers was "almost perfect." Accuracy between ChatGPT answers and CPGs recommendations was slight, demonstrating agreement in 33% of recommendations. CONCLUSION: ChatGPT performed poorly in internal consistency and accuracy of the indications generated compared to clinical practice guideline recommendations for lumbosacral radicular pain. [ABSTRACT FROM AUTHOR]

Various applications in computational linguistics and artificial intelligence rely on high-performing word sense disambiguation techniques to solve challenging tasks such as information retrieval, machine translation, question answering, and document clustering. While text comprehension is intuitive for humans, machines face tremendous challenges in processing and interpreting a human's natural language. This paper presents a novel knowledge-based word sense disambiguation algorithm, namely Sequential Contextual Similarity Matrix Multiplication (SCSMM). The SCSMM algorithm combines semantic similarity, heuristic knowledge, and document context to respectively exploit the merits of local sense-based context between consecutive terms, human knowledge about terms, and a document's main topic in disambiguating terms. Unlike other algorithms, the SCSMM algorithm guarantees the capture of the maximum sentence context while maintaining the terms' order within the sentence. The proposed algorithm outperformed all other algorithms when disambiguating nouns on the combined gold standard datasets, while demonstrating comparable results to current state-of-the-art word sense disambiguation systems when dealing with each dataset separately. Furthermore, the paper discusses the impact of granularity level, ambiguity rate, sentence size, and part of speech distribution on the performance of the proposed algorithm. • Semantic similarity affects the overall performance of knowledge-based Word Sense Disambiguation (WSD) systems. • With Semantic similarity, sense heuristics, and document context, we designed a novel knowledge-based word sense disambiguation algorithm. • The Sequential Contextual Similarity Matrix Multiplication (SCSMM) algorithm captures the maximum sentence context while maintaining the words' order. • The SCSMM algorithm outperforms current WSD systems when disambiguating nouns. [ABSTRACT FROM AUTHOR]

Copyright of Scientific Journal of Library, Archives & Information (SJLAI) is the property of Cairo University, Faculty of Arts - Documents & information Technology Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This editorial explores the profound impact of ChatGPT, powered by OpenAI's GPT-3.5 architecture, on the landscape of research across diverse fields (Smith & Johnson, 2021). ChatGPT has emerged as a transformative tool for researchers and scholars, offering unparalleled access to information, fostering collaboration, and enhancing communication skills (Brown & Davis, 2020). It accelerates literature reviews, aids in idea generation, and facilitates interdisciplinary research (Chen & Kim, 2019). However, the adoption of ChatGPT in research is not without its challenges (Johnson & White, 2018). Ethical considerations, biases in responses, and data privacy concerns require vigilant attention. Despite these limitations, ChatGPT represents a significant leap forward in human-machine collaboration, empowering researchers to explore new avenues and streamline various aspects of their work (OpenAI, 2023). The future of research lies in harnessing the capabilities of ChatGPT while remaining cognizant of its limitations and ensuring that its integration aligns with evolving research needs. Researchers and developers must collaborate to realize the full potential of this transformative technology in academia. [ABSTRACT FROM AUTHOR]

Rising incidence and mortality of cancer have led to an incremental amount of research in the field. To learn from preexisting data, it has become important to capture maximum information related to disease type, stage, treatment, and outcomes. Medical imaging reports are rich in this kind of information but are only present as free text. The extraction of information from such unstructured text reports is labor-intensive. The use of Natural Language Processing (NLP) tools to extract information from radiology reports can make it less time-consuming as well as more effective. In this study, we have developed and compared different models for the classification of lung carcinoma reports using clinical concepts. This study was approved by the institutional ethics committee as a retrospective study with a waiver of informed consent. A clinical concept-based classification pipeline for lung carcinoma radiology reports was developed using rule-based as well as machine learning models and compared. The machine learning models used were XGBoost and two more deep learning model architectures with bidirectional long short-term neural networks. A corpus consisting of 1700 radiology reports including computed tomography (CT) and positron emission tomography/computed tomography (PET/CT) reports were used for development and testing. Five hundred one radiology reports from MIMIC-III Clinical Database version 1.4 was used for external validation. The pipeline achieved an overall F1 score of 0.94 on the internal set and 0.74 on external validation with the rule-based algorithm using expert input giving the best performance. Among the machine learning models, the Bi-LSTM_dropout model performed better than the ML model using XGBoost and the Bi-LSTM_simple model on internal set, whereas on external validation, the Bi-LSTM_simple model performed relatively better than other 2. This pipeline can be used for clinical concept-based classification of radiology reports related to lung carcinoma from a huge corpus and also for automated annotation of these reports. [ABSTRACT FROM AUTHOR]

The article discusses the role of Information and Communication Technology (ICT) in libraries, emphasizing its impact on modernizing services and improving user experiences. It highlights the global adoption of ICT solutions in academic libraries, such as automated systems, digital repositories, and virtual reference services. Despite advancements, challenges like inadequate infrastructure and limited funding persist.

There is an increasing interest in developing artificial intelligence (AI) systems to process and interpret electronic health records (EHRs). Natural language processing (NLP) powered by pretrained language models is the key technology for medical AI systems utilizing clinical narratives. However, there are few clinical language models, the largest of which trained in the clinical domain is comparatively small at 110 million parameters (compared with billions of parameters in the general domain). It is not clear how large clinical language models with billions of parameters can help medical AI systems utilize unstructured EHRs. In this study, we develop from scratch a large clinical language model—GatorTron—using >90 billion words of text (including >82 billion words of de-identified clinical text) and systematically evaluate it on five clinical NLP tasks including clinical concept extraction, medical relation extraction, semantic textual similarity, natural language inference (NLI), and medical question answering (MQA). We examine how (1) scaling up the number of parameters and (2) scaling up the size of the training data could benefit these NLP tasks. GatorTron models scale up the clinical language model from 110 million to 8.9 billion parameters and improve five clinical NLP tasks (e.g., 9.6% and 9.5% improvement in accuracy for NLI and MQA), which can be applied to medical AI systems to improve healthcare delivery. The GatorTron models are publicly available at: https://catalog.ngc.nvidia.com/orgs/nvidia/teams/clara/models/gatortron_og. [ABSTRACT FROM AUTHOR]

Web search is widely used to find online medical advice. As such, health-related information access requires retrieval algorithms capable of promoting reliable documents and filtering out unreliable ones. To this end, different types of components, such as query-document matching features, passage relevance estimation and AI-based reliability estimators, need to be combined. In this paper, we propose an entire pipeline for misinformation detection, based on the fusion of multiple content-based features. We present experiments which study the influence of each pipeline stage for the target task. Our technological solution incorporates signals from technologies derived from diverse research fields, including search, deep learning for natural language processing, as well as advanced supervised and unsupervised learning. To combine evidence, different score fusion strategies are compared, including unsupervised rank fusion techniques and learning-to-rank methods. The reference framework for empirically validating our solution is the TREC Health Misinformation Track, which provides several challenging subtasks that foster research on the identification of reliable and correct information for health-related decision making tasks. More specifically, we address a total recall task, the goal of which is to identify all the documents conveying incorrect information for a specific set of topics, and an ad-hoc retrieval task, aiming to rank credible and correct information over incorrect information. All variants are evaluated with an assorted set of effectiveness metrics, which includes standard search measures, such as R-Precision, Average Precision or Normalised Discounted Cumulative Gain, and innovative metrics based on the compatibility between the ranked output and two reference rankings composed of helpful and harmful documents, respectively. Our experiments demonstrate the effectiveness of the proposed pipeline stages and indicate that sophisticated supervised fusion methods do not fare better than simpler fusion alternatives. Additionally, for reliability estimation, unsupervised textual similarity performs better than textual classification based on supervised learning. The results also show that the presented approach is highly competitive when compared with state-of-the-art solutions for the same problem. • A complete system for health misinformation detection is proposed. • Several content-based features are proposed for identifying health misinformation. • The performance of the different features and against external baselines is reported. • New metrics considering harmfulness and helpfulness of retrieved documents are used. • The technology developed is freely available for other researchers or stakeholders. [ABSTRACT FROM AUTHOR]

The term "Frequently asked questions" (FAQ) refers to a query that is asked repeatedly and produces a manually constructed response. It is one of the most important factors influencing customer repurchase and brand loyalty; thus, most industry domains invest heavily in it. This has led to deep-learning-based retrieval models being studied. However, training a model and creating a database specializing in each industry domain comes at a high cost, especially when using a chatbot-based conversation system, as a large amount of resources must be continuously input for the FAQ system's maintenance. It is also difficult for small- and medium-sized companies and national institutions to build individualized training data and databases and obtain satisfactory results. As a result, based on the deep learning information retrieval module, we propose a method of returning responses to customer inquiries using only data that can be easily obtained from companies. We hybridize dense embedding and sparse embedding in this work to make it more robust in professional terms, and we propose new functions to adjust the weight ratio and scale the results returned by the two modules. [ABSTRACT FROM AUTHOR]

The Internet, much like our universe, is ever-expanding. Information, in the most varied formats, is continuously added to the point of information overload. Consequently, the ability to navigate this ocean of data is crucial in our day-to-day lives, with familiar tools such as search engines carving a path through this unknown. In the research world, articles on a myriad of topics with distinct complexity levels are published daily, requiring specialized tools to facilitate the access and assessment of the information within. Recent endeavors in artificial intelligence, and in natural language processing in particular, can be seen as potential solutions for breaking information overload and provide enhanced search mechanisms by means of advanced algorithms. As the advent of transformer-based language models contributed to a more comprehensive analysis of both text-encoded intents and true document semantic meaning, there is simultaneously a need for additional computational resources. Information retrieval methods can act as low-complexity, yet reliable, filters to feed heavier algorithms, thus reducing computational requirements substantially. In this work, a new search engine is proposed, addressing machine reading at scale in the context of scientific and academic research. It combines state-of-the-art algorithms for information retrieval and reading comprehension tasks to extract meaningful answers from a corpus of scientific documents. The solution is then tested on two current and relevant topics, cybersecurity and energy, proving that the system is able to perform under distinct knowledge domains while achieving competent performance. [ABSTRACT FROM AUTHOR]

A library's website is a virtual point of contact for interacting with its patrons. Ensuring a library's website has easily findable content is critical for providing access to library resources and highlighting services and events. One tool for assisting with content findability is a chatbot, a form of artificial intelligence software. In this case study, Lehman College's Leonard Lief Library implemented Ivy, a proprietary educational software chatbot on its website, the first of its kind for an academic library. This chatbot functioned as a new tool that assisted users seeking information and provided insight to librarians about the kinds of topics students search for via the library website. This article provides the first detailed description in the literature of an implementation of a proprietary chatbot for an academic library. [ABSTRACT FROM AUTHOR]

Synthetic speech's applications sector is rapidly growing, as well as the quality of TTS systems is continuously improving. Speech synthesis solutions are becoming relatively cheap for average users, making them more appropriate for regular usage, especially as NLP, Machine Learning, and Artificial Intelligence continue to develop where Synthetic speech may also be utilised in a variety of industries, and with effective integration, money can indeed be saved. [ABSTRACT FROM AUTHOR]

Contractors responsible for the whole execution of engineering, procurement, and construction (EPC) projects are exposed to multiple risks due to various unbalanced contracting methods such as lump-sum turn-key and low-bid selection. Although systematic risk management approaches are required to prevent unexpected damage to the EPC contractors in practice, there were no comprehensive digital toolboxes for identifying and managing risk provisions for ITB and contract documents. This study describes two core modules, Critical Risk Check (CRC) and Term Frequency Analysis (TFA), developed as a digital EPC contract risk analysis tool for contractors, using artificial intelligence and text-mining techniques. The CRC module automatically extracts risk-involved clauses in the EPC ITB and contracts by the phrase-matcher technique. A machine learning model was built in the TFA module for contractual risk extraction by using the named-entity recognition (NER) method. The risk-involved clauses collected for model development were converted into a database in JavaScript Object Notation (JSON) format, and the final results were saved in pickle format through the digital modules. In addition, optimization and reliability validation of these modules were performed through Proof of Concept (PoC) as a case study, and the modules were further developed to a cloud-service platform for application. The pilot test results showed that risk clause extraction accuracy rates with the CRC module and the TFA module were about 92% and 88%, respectively, whereas the risk clause extraction accuracy rates manually by the engineers were about 70% and 86%, respectively. The time required for ITB analysis was significantly shorter with the digital modules than by the engineers. [ABSTRACT FROM AUTHOR]