Correction: Advancing predictive content analysis: a natural language processing and machine learning approach to television script data

Background. There is growing evidence that social and behavioral determinants of health (SBDH) play a substantial effect in a wide range of health outcomes. Electronic health records (EHRs) have been widely employed to conduct observational studies in the age of artificial intelligence (AI). However, there has been limited review into how to make the most of SBDH information from EHRs using AI approaches.Methods. A systematic search was conducted in six databases to find relevant peer-reviewed publications that had recently been published. Relevance was determined by screening and evaluating the articles. Based on selected relevant studies, a methodological analysis of AI algorithms leveraging SBDH information in EHR data was provided.Results. Our synthesis was driven by an analysis of SBDH categories, the relationship between SBDH and healthcare-related statuses, natural language processing (NLP) approaches for extracting SBDH from clinical notes, and predictive models using SBDH for health outcomes.Discussion. The associations between SBDH and health outcomes are complicated and diverse; several pathways may be involved. Using NLP technology to support the extraction of SBDH and other clinical ideas simplifies the identification and extraction of essential concepts from clinical data, efficiently unlocks unstructured data, and aids in the resolution of unstructured data-related issues.Conclusion. Despite known associations between SBDH and diseases, SBDH factors are rarely investigated as interventions to improve patient outcomes. Gaining knowledge about SBDH and how SBDH data can be collected from EHRs using NLP approaches and predictive models improves the chances of influencing health policy change for patient wellness, ultimately promoting health and health equity.

Nowadays, the dissemination of news information has become more rapid, liberal, and open to the public. People can find what they want to know more and more easily from a variety of sources, including traditional news outlets and new social media platforms. However, at a time when our lives are glutted with all kinds of news, we cannot help but doubt the veracity and legitimacy of these news sources; meanwhile, we also need to guard against the possible impact of various forms of fake news. To combat the spread of misinformation, more and more researchers have turned to natural language processing (NLP) approaches for effective fake news detection. However, in the face of increasingly serious fake news events, existing detection methods still need to be continuously improved. This study proposes a modified proof-of-concept model named NER-SA, which integrates natural language processing (NLP) and named entity recognition (NER) to conduct the in-domain and cross-domain analysis of fake news detection with the existing three datasets simultaneously. The named entities associated with any particular news event exist in a finite and available evidence pool. Therefore, entities must be mentioned and recognized in this entity bank in any authentic news articles. A piece of fake news inevitably includes only some entitlements in the entity bank. The false information is deliberately fabricated with fictitious, imaginary, and even unreasonable sentences and content. As a result, there must be differences in statements, writing logic, and style between legitimate news and fake news, meaning that it is possible to successfully detect fake news. We developed a mathematical model and used the simulated annealing algorithm to find the optimal legitimate area. Comparing the detection performance of the NER-SA model with current state-of-the-art models proposed in other studies, we found that the NER-SA model indeed has superior performance in detecting fake news. For in-domain analysis, the accuracy increased by an average of 8.94% on the LIAR dataset and 19.36% on the fake or real news dataset, while the F1-score increased by an average of 24.04% on the LIAR dataset and 19.36% on the fake or real news dataset. In cross-domain analysis, the accuracy and F1-score for the NER-SA model increased by an average of 28.51% and 24.54%, respectively, across six domains in the FakeNews AMT dataset. The findings and implications of this study are further discussed with regard to their significance for improving accuracy, understanding context, and addressing adversarial attacks. The development of stylometric detection based on NLP approaches using NER techniques can improve the effectiveness and applicability of fake news detection.

Requirements engineering is the first phase in software development life cycle and it also plays one of the most important and critical roles. Requirement document mainly contains both functional requirements and non-functional requirements. Non-functional requirements are significant to describe the properties and constraints of the system. Early identification of Non-functional requirement has direct impact on the system architecture and initial design decision. Practically, non-functional requirements are extracted manually from the document. This makes it tedious, time-consuming task and prone to various errors. In this paper, we propose an automatic approach to identify and classify non-functional requirements using semantic and syntactic analysis with machine learning approaches from unconstrained documents. We used A dataset of public requirements documents (PURE) that consists of 79 unconstrained requirements documents in different forms. In our approach, features were extracted from the requirement sentences using four different natural language processing methods including statistical and state-ofthe-art semantic analysis presented by Google word2vec and bidirectional encoder representations from transformers models. The adopted approach can efficiently classify non-functional requirements with an accuracy between 84% and 87% using statistical vectorization method and 88% to 92% using word embedding semantic methods. Furthermore, by fusing different models trained on different features, the accuracy improves by 2.4% compared with the best individual classifier. INDEX TERMS Software requirement, Machine learning, Natural language processing.

Machine learning techniques have long been the foundations of speech processing. Bayesian classiflcation, decision trees, unsupervised clustering, the EM algorithm, maximum entropy, etc. are all part of existing speech recognition systems. The success of statistical speech recognition has led to the rise of statistical and empirical methods in natural language processing. Indeed, many of the machine learning techniques used in language processing, from statistical part-of-speech tagging to the noisy channel model for machine translation have roots in work conducted in the speech fleld. However, advances in learning theory and algorithmic machine learning approaches in recent years have led to signiflcant changes in the direction and emphasis of the statistical and learning centered research in natural language processing and made a mark on natural language and speech processing. Approaches such as memory based learning, a range of linear classiflers such as Boosting, SVMs and SNoW and others have been successfully applied to a broad range of natural language problems, and these now inspire new research in speech retrieval and recognition. We have seen an increasingly close collaboration between voice and language processing researchers in some of the shared tasks such as spontaneous speech recognition and understanding, voice data information extraction, and machine translation. The purpose of this special issue was to invite speech and language researchers to communicate with each other, and with the machine learning community on the latest machine learning advances in their work. The call for papers was met with great enthusiasm from the speech and natural language community. Thirty six submissions were received; each paper was reviewed by at least three reviewers. Only ten papers were selected re∞ecting not only some of the best work on machine learning in the areas of natural language and spoken language processing but also what we view as a collection of papers that represent current trends in these areas of research both from the perspective of

IntroductionPresence of a firearm is associated with increased risk of violence and suicide. United States military veterans are at disproportionate risk of suicide. Routine healthcare provider screening of firearm access may prompt counseling on safe storage and handling of firearms. The objective of this study was to determine the frequency with which Veterans Health Administration (VHA) healthcare providers document firearm access in electronic health record (EHR) clinical notes, and whether this varied by patient characteristics.MethodsThe study sample is a post-9–11 cohort of veterans in their first year of VHA care, with at least one outpatient care visit between 2012–2017 (N = 762,953). Demographic data, veteran military service characteristics, and clinical comorbidities were obtained from VHA EHR. We extracted clinical notes for outpatient visits to primary, urgent, or emergency clinics (total 105,316,004). Natural language processing and machine learning (ML) approaches were used to identify documentation of firearm access. A taxonomy of firearm terms was identified and manually annotated with text anchored by these terms, and then trained the ML algorithm. The random-forest algorithm achieved 81.9% accuracy in identifying documentation of firearm access.ResultsThe proportion of patients with EHR-documented access to one or more firearms during their first year of care in the VHA was relatively low and varied by patient characteristics. Men had significantly higher documentation of firearms than women (9.8% vs 7.1%; P < .001) and veterans >50 years old had the lowest (6.5%). Among veterans with any firearm term present, only 24.4% were classified as positive for access to a firearm (24.7% of men and 20.9% of women).ConclusionNatural language processing can identify documentation of access to firearms in clinical notes with acceptable accuracy, but there is a need for investigation into facilitators and barriers for providers and veterans to improve a systemwide process of firearm access screening. Screening, regardless of race/ethnicity, gender, and age, provides additional opportunities to protect veterans from self-harm and violence.

Geriatric syndromes (GS) are complex conditions that affect older adults and often require multidisciplinary assessment. Natural language processing (NLP) has emerged as a promising tool for extracting relevant clinical information from unstructured text in electronic health records (EHRs). However, the application of NLP in detecting and monitoring GS remains an evolving area of research. This systematic review explores the role of NLP in the identification and analysis of GS, examining its applications, methodologies, and effectiveness. Furthermore, this review discusses the existing challenges, limitations, and future directions to advance NLP applications in the GS research. We conducted a systematic literature search across ten databases to identify studies that applied NLP to GS detection. Articles were screened using predefined inclusion and exclusion criteria, and relevant studies were evaluated for quality using PROBAST. Data were extracted on study characteristics, datasets, annotation processes, NLP approaches, performance metrics, population demographics, and clinical applications. A PRISMA flow diagram was used to illustrate the study selection process. A total of 65 studies were included, where the majority of the studies used traditional rule-based and machine learning approaches. Publicly available datasets were scarce, and most studies used their private dataset, leading to significant variability in data sources and formats. Annotation methodologies differed across studies, with minimal shared guidelines or standards, making direct comparisons challenging. Performance metrics varied across syndromes, with F1-score, precision, and recall as the most commonly reported. Key challenges included the lack of dataset uniformity, differences in annotation practices, and the absence of external validation. NLP has shown potential in GS analysis, particularly for the detection of syndromes and epidemiological research. However, the majority of studies only focused on one syndrome, and variability in dataset availability, annotation processes, and model performance present challenges to broader implementation. Future research should focus on improving the comprehensiveness of GS identification, dataset standardisation, enhancing model generalisability, and integrating NLP approaches into clinical workflows.

Through the creation of data-driven, customized, and adaptive learning experiences, artificial intelligence (AI) is changing the face of education. In order to evaluate the current practices, trends, and difficulties in AI-assisted learning, this study provides a thorough analysis of 26 recent works. According to the research, there is a lot of emphasis on machine learning (ML) and natural language processing (NLP) approaches, which are used in tools like chatbots, automated feedback systems, and adaptive learning platforms. The application field is dominated by higher education, with particular emphasis on computer programming and language acquisition. Significant gaps still exist, nevertheless, such as the lack of a consensus definition for AI-assisted learning, the little investigation of multimodal integration, and the lack of focus on moral issues like algorithmic prejudice and data privacy. Furthermore, rather of using actual learning settings, the majority of research depend on simulations or small-scale setups. In order to overcome these constraints, this paper suggests an integrative architecture that combines multimodal inputs such as text, audio, and video, explainable AI (XAI) for transparency, and ethical governance. Additionally, it promotes more involvement of underrepresented fields including K–12 and vocational education as well as research into hybrid AI– human teaching methods. This paper provides a path for the moral, practical, and inclusive development of AI-assisted learning systems in addition to synthesizing existing information.

Gojek, a leading proponent of on-demand services in Indonesia, has garnered a total of 142 million downloads. However, it has received the fewest reviews compared to other on-demand applications. The objective of this research is to identify sentiment in Gojek application user reviews on Google Playstore using Natural Language Processing (NLP) approaches and machine learning algorithms through the Orange platform. The reviews utilized in this study were collected in June 2025 and encompass a total of 3,615 data points, including 2,892 training data and 723 testing data. Sentiments are classified into two categories based on their ratings: positive (rating 4-5) and negative (rating 1-2). The research process is comprised of four primary stages: data collection and labeling, text pre-processing, feature transformation using TF-IDF, and testing five classification algorithms: neural network, naïve Bayes, random forest, decision tree, and k-nearest neighbors. The evaluation results indicate that the Neural Network model demonstrates optimal performance, exhibiting 93.20% accuracy, 93.00% F1-score, and 75.80% MCC. These findings suggest that the NLP approach can be utilized effectively to comprehend user perceptions of applications. It is anticipated that this research will assist Gojek developers in the monitoring and enhancement of service quality, with this enhancement being informed by user feedback.

Cyberbullying has become a ubiquitous menace in our digitally connected society, requiring strong detection and classification systems. This study presents a multi-tiered system that reliably detects and classifies instances of cyberbullying on a variety of platforms by utilising cutting-edge machine learning and natural language processing approaches. Our algorithm, which was trained on a wide range of datasets, shows excellent accuracy in differentiating between instances of cyberbullying and non-bullying situations while taking linguistic and cultural quirks into account. Furthermore, our flexible system guarantees applicability by adjusting to changing cyberbullying patterns. By promoting safer and more inclusive digital communities, our research helps to design proactive treatments that lessen the effects of online harassment. This study introduces a robust multi-tiered system designed for the detection and classification of cyberbullying across diverse digital platforms. Leveraging state-of-the-art machine learning and natural language processing techniques, our algorithm, trained on extensive datasets, exhibits exceptional accuracy in distinguishing cyberbullying instances from non-bullying scenarios while accommodating linguistic and cultural nuances. The system’s adaptability to evolving cyberbullying patterns ensures continued efficacy. By fostering safer and more inclusive online environments, our research contributes to proactive measures and mitigates the impact of digital harassment.

Fake news has become a significant social problem that affects public opinion and social trust. The dissemination of misinformation at lightning speed through online media channels presents a serious problem in distinguishing between credible and deceptive content. Much research has been done on machine learning and natural language processing (NLP) approaches to create automated detection systems that address this problem. These methods classify news stories as synthetic or legitimate based on statistical, contextual, and language characteristics. Several machine learning techniques are presented in this book, including deeper, more complex models as well as more conventional classifiers like Logistic Regression (LR), Naïve Bayes (NB), Support Vector Machines (SVM), and Decision Trees. Additionally, the hybrid models that combine ensemble learning and natural language processing (NLP) are showcased for their potential to improve classification accuracy and dependability. Feature extraction techniques like word embeddings, N-grams, and Term Frequency-Inverse Document Frequency (TF-IDF) are credited with organizing textual data into machine learning inputs. In addition, network-based techniques and sentiment analysis are examined as substitute techniques for pattern recognition in the fight against false information. The findings provide strong evidence that combining statistics and deep learning techniques enhances the effectiveness and precision of false news detection. This study establishes the groundwork for future research to create robust and scalable systems for identifying fake news by shedding light on the capabilities and limitations of various approaches.

Nowadays, most of the information available on the web is in Natural Language. Extracting such knowledge from Natural Language text is an essential work and a very remarkable research topic in the Semantic Web field. The logic programming language Prolog, based on the definite-clause formalism, is a useful tool for implementing a Natural Language Processing (NLP) systems. However, web-based services for NLP have also been developed recently, and they represent an important alternative to be considered. In this paper we present the comparison between two different approaches in NLP, for the automatic creation of an OWL ontology supporting the semantic annotation of text. The first one is a pure Prolog approach, based on grammar and logic analysis rules. The second one is based on Watson Relationship Extraction service of IBM Cloud platform Bluemix. We evaluate the two approaches in terms of performance, the quality of NLP result, OWL completeness and richness.

Challenges and Opportunities of Using Transformer-Based Multi-Task Learning in NLP Through ML Lifecycle: A Position Paper

The concept of "quality of life" (QoL) encompasses all aspects of people's standard of living, including economic, social, or health-related factors, as well as their perceptions of their own lives. Although the growing application of Artificial Intelligence (AI) and Machine Learning (ML) techniques in processing and modeling the diverse datasets associated with these domains, there remains a significant challenge in addressing different issues in QoL area of research and in fully harnessing these technologies to improve QoL research outcomes. Despite the technological advancements, current research endeavors often overlook the complex, multifaceted nature of QoL study. This oversight results in fragmented insights and leaves significant areas underexplored. In this work, we conducted a systematic literature review (SLR) to investigate the contribution of AI to QoL studies. For this, we collected 68 research works published between 2008 and 2022. This review covers a range of research questions about the objectives and methods of studies on QoL, the sources and types of data utilized, and the advancements made through the application of natural language processing (NLP), ML, deep learning (DL), statistical models, and semantic approaches. The goal of this review is to tackle the prevalent ambiguity in QoL dimensions, synthesize the research findings, and highlight the contributions, advancements, and most innovative approaches in the field. Moreover, we identify gaps and limitations in the current literature and suggest potential areas for future research, aiming to inspire more cohesive and comprehensive approaches to studying QoL using AI and ML techniques.

BackgroundLarge language models have had a huge impact on natural language processing (NLP) in recent years. However, their application in epidemiological research is still limited to the analysis of electronic health records and social media data.ObjectivesTo demonstrate the potential of NLP beyond these domains, we aimed to develop prediction models based on texts collected from an epidemiological cohort and compare their performance to classical regression methods.MethodsWe used data from the British National Child Development Study, where 10,567 children aged 11 years wrote essays about how they imagined themselves as 25-year-olds. Overall, 15% of the data set was set aside as a test set for performance evaluation. Pretrained language models were fine-tuned using AutoTrain (Hugging Face) to predict current reading comprehension score (range: 0-35) and future BMI and physical activity (active vs inactive) at the age of 33 years. We then compared their predictive performance (accuracy or discrimination) with linear and logistic regression models, including demographic and lifestyle factors of the parents and children from birth to the age of 11 years as predictors.ResultsNLP clearly outperformed linear regression when predicting reading comprehension scores (root mean square error: 3.89, 95% CI 3.74-4.05 for NLP vs 4.14, 95% CI 3.98-4.30 and 5.41, 95% CI 5.23-5.58 for regression models with and without general ability score as a predictor, respectively). Predictive performance for physical activity was similarly poor for the 2 methods (area under the receiver operating characteristic curve: 0.55, 95% CI 0.52-0.60 for both) but was slightly better than random assignment, whereas linear regression clearly outperformed the NLP approach when predicting BMI (root mean square error: 4.38, 95% CI 4.02-4.74 for NLP vs 3.85, 95% CI 3.54-4.16 for regression). The NLP approach did not perform better than simply assigning the mean BMI from the training set as a predictor.ConclusionsOur study demonstrated the potential of using large language models on text collected from epidemiological studies. The performance of the approach appeared to depend on how directly the topic of the text was related to the outcome. Open-ended questions specifically designed to capture certain health concepts and lived experiences in combination with NLP methods should receive more attention in future epidemiological studies.

One of the most widely used approaches in natural language processing and information retrieval is the so-called bag-of-words model. A common component of such methods is the removal of uninformative words, commonly referred to as stopwords. Currently, most practitioners use manually curated stopword lists. This approach is problematic because it cannot be readily generalized across knowledge domains or languages. As a result of the difficulty in rigorously defining stopwords, there have been few systematic studies on the effect of stopword removal on algorithm performance, which is reflected in the ongoing debate on whether to keep or remove stopwords. Here we address this challenge by formulating an information theoretic framework that automatically identifies uninformative words in a corpus. We show that our framework not only outperforms other stopword heuristics, but also allows for a substantial reduction of document size in applications of topic modelling. Our findings can be readily generalized to other bag-of-words-type approaches beyond language such as in the statistical analysis of transcriptomics, audio or image corpora. To better extract meaning from natural language, some less informative words can be removed before a model is trained, which is usually done by using manually curated lists of stopwords. A new information theoretic approach can identify uninformative words automatically and more accurately.