Natural Language Processing Framework Research Articles

Linguistic-based Mild Cognitive Impairment detection using Informative Loss

This paper presents a deep learning method using Natural Language Processing (NLP) techniques, to distinguish between Mild Cognitive Impairment (MCI) and Normal Cognitive (NC) conditions in older adults. We propose a framework that analyzes transcripts generated from video interviews collected within the I-CONECT study project, a randomized controlled trial aimed at improving cognitive functions through video chats. Our proposed NLP framework consists of two Transformer-based modules, namely Sentence Embedding (SE) and Sentence Cross Attention (SCA). First, the SE module captures contextual relationships between words within each sentence. Subsequently, the SCA module extracts temporal features from a sequence of sentences. This feature is then used by a Multi-Layer Perceptron (MLP) for the classification of subjects into MCI or NC. To build a robust model, we propose a novel loss function, called InfoLoss, that considers the reduction in entropy by observing each sequence of sentences to ultimately enhance the classification accuracy. The results of our comprehensive model evaluation using the I-CONECT dataset show that our framework can distinguish between MCI and NC with an average area under the curve of 84.75%.

Impact of an Artificial Intelligence in Language Learning - A survey

Bully Scan, an artificial intelligence system for identifying offensive language on social media, is proposed in "A Natural Language Processing and Machine Learning-Based Framework to Automatically Identify Cyberbullying. This paradigm, which aims to reduce the negative impacts of cyberbullying and encourage healthy online interactions, is a critical step in using AI for social well-being. The paper, "Research and Practice of Hybrid Teaching Based on AI technology for Foreign Language Translation," offers a novel strategy for teaching foreign languages through the incorporation of AI. The project investigates a hybrid teaching approach that combines AI-powered language translation tools with conventional classroom training. This method seeks to improve accuracy and efficiency of language learning by providing real-time translation support. Through the use of AI technologies, such as machine learning and natural language processing, the system offers students helpful translation assistance, enhancing their educational experience. The study demonstrates encouraging outcomes in terms of raising students' proficiency and effectiveness in translation in a blended learning setting.
 The paper "Modular Design of English Pronunciation Level Evaluation System Based on Deep Learning Algorithm" offers a novel method for determining pronunciation levels in English by utilizing deep learning algorithms. The study uses techniques like support vector machines and BP neural networks to address the problem of computational intensity in language teaching technologies. Through the application of machine deep learning, the system seeks to improve the precision and efficacy of pronunciation level assessments, providing insightful information for the development of theories for foreign language instruction in the rapidly changing field of artificial intelligence. The study's modular design approach offers a viable foundation for enhancing pronunciation assessment in language instruction.

A large language model-based generative natural language processing framework fine-tuned on clinical notes accurately extracts headache frequency from electronic health records.

To develop a natural language processing (NLP) algorithm that can accurately extract headache frequency from free-text clinical notes. Headache frequency, defined as the number of days with any headache in a month (or 4 weeks), remains a key parameter in the evaluation of treatment response to migraine preventive medications. However, due to the variations and inconsistencies in documentation by clinicians, significant challenges exist to accurately extract headache frequency from the electronic health record (EHR) by traditional NLP algorithms. This was a retrospective cross-sectional study with patients identified from two tertiary headache referral centers, Mayo Clinic Arizona and Mayo Clinic Rochester. All neurology consultation notes written by 15 specialized clinicians (11 headache specialists and 4 nurse practitioners) between 2012 and 2022 were extracted and 1915 notes were used for model fine-tuning (90%) and testing (10%). We employed four different NLP frameworks: (1) ClinicalBERT (Bidirectional Encoder Representations from Transformers) regression model, (2) Generative Pre-Trained Transformer-2 (GPT-2) Question Answering (QA) model zero-shot, (3) GPT-2 QA model few-shot training fine-tuned on clinical notes, and (4) GPT-2 generative model few-shot training fine-tuned on clinical notes to generate the answer by considering the context of included text. The mean (standard deviation) headache frequency of our training and testing datasets were 13.4 (10.9) and 14.4 (11.2), respectively. The GPT-2 generative model was the best-performing model with an accuracy of 0.92 (0.91, 0.93, 95% confidence interval [CI]) and R2 score of 0.89 (0.87, 0.90, 95% CI), and all GPT-2-based models outperformed the ClinicalBERT model in terms of exact matching accuracy. Although the ClinicalBERT regression model had the lowest accuracy of 0.27 (0.26, 0.28), it demonstrated a high R2 score of 0.88 (0.85, 0.89), suggesting the ClinicalBERT model can reasonably predict the headache frequency within a range of ≤ ± 3 days, and the R2 score was higher than the GPT-2 QA zero-shot model or GPT-2 QA model few-shot training fine-tuned model. We developed a robust information extraction model based on a state-of-the-art large language model, a GPT-2 generative model that can extract headache frequency from EHR free-text clinical notes with high accuracy and R2 score. It overcame several challenges related to different ways clinicians document headache frequency that were not easily achieved by traditional NLP models. We also showed that GPT-2-based frameworks outperformed ClinicalBERT in terms of accuracy in extracting headache frequency from clinical notes. To facilitate research in the field, we released the GPT-2 generative model and inference code with open-source license of community use in GitHub. Additional fine-tuning of the algorithm might be required when applied to different health-care systems for various clinical use cases.

Generative Pre-Trained Transformer-Empowered Healthcare Conversations: Current Trends, Challenges, and Future Directions in Large Language Model-Enabled Medical Chatbots

This review explores the transformative integration of artificial intelligence (AI) and healthcare through conversational AI leveraging Natural Language Processing (NLP). Focusing on Large Language Models (LLMs), this paper navigates through various sections, commencing with an overview of AI’s significance in healthcare and the role of conversational AI. It delves into fundamental NLP techniques, emphasizing their facilitation of seamless healthcare conversations. Examining the evolution of LLMs within NLP frameworks, the paper discusses key models used in healthcare, exploring their advantages and implementation challenges. Practical applications in healthcare conversations, from patient-centric utilities like diagnosis and treatment suggestions to healthcare provider support systems, are detailed. Ethical and legal considerations, including patient privacy, ethical implications, and regulatory compliance, are addressed. The review concludes by spotlighting current challenges, envisaging future trends, and highlighting the transformative potential of LLMs and NLP in reshaping healthcare interactions.

FedFSA: Hybrid and federated framework for functional status ascertainment across institutions

IntroductionPatients' functional status assesses their independence in performing activities of daily living, including basic ADLs (bADL), and more complex instrumental activities (iADL). Existing studies have discovered that patients’ functional status is a strong predictor of health outcomes, particularly in older adults. Depite their usefulness, much of the functional status information is stored in electronic health records (EHRs) in either semi-structured or free text formats. This indicates the pressing need to leverage computational approaches such as natural language processing (NLP) to accelerate the curation of functional status information. In this study, we introduced FedFSA, a hybrid and federated NLP framework designed to extract functional status information from EHRs across multiple healthcare institutions. MethodsFedFSA consists of four major components: 1) individual sites (clients) with their private local data, 2) a rule-based information extraction (IE) framework for ADL extraction, 3) a BERT model for functional status impairment classification, and 4) a concept normalizer. The framework was implemented using the OHNLP Backbone for rule-based IE and open-source Flower and PyTorch library for federated BERT components. For gold standard data generation, we carried out corpus annotation to identify functional status-related expressions based on ICF definitions. Four healthcare institutions were included in the study. To assess FedFSA, we evaluated the performance of category- and institution-specific ADL extraction across different experimental designs. ResultsADL extraction performance ranges from an F1-score of 0.907 to 0.986 for bADL and 0.825 to 0.951 for iADL across the four healthcare sites. The performance for ADL extraction with impairment ranges from an F1-score of 0.722 to 0.954 for bADL and 0.674 to 0.813 for iADL across four healthcare sites. For category-specific ADL extraction, laundry and transferring yielded relatively high performance, while dressing, medication, bathing, and continence achieved moderate-high performance. Conversely, food preparation and toileting showed low performance. ConclusionNLP performance varied across ADL categories and healthcare sites. Federated learning using a FedFSA framework performed higher than non-federated learning for impaired ADL extraction at all healthcare sites. Our study demonstrated the potential of the federated learning framework in functional status extraction and impairment classification in EHRs, exemplifying the importance of a large-scale, multi-institutional collaborative development effort.

Machine learning of public sentiments towards wind energy in Norway

AbstractAcross Europe, negative public opinion has and may continue to limit the deployment of renewable energy infrastructure required for the transition to net‐zero energy systems. Understanding public sentiment and its spatio‐temporal variations is as such important for decision‐making and for developing socially accepted energy systems. In this study, we apply a sentiment classification model based on a machine learning framework for natural language processing, NorBERT, on data collected from Twitter between 2006 and 2022 to analyse the case of wind power opposition in Norway. From the 68,828 tweets with geospatial information, we show how discussions about wind power intensified in 2018/2019 together with a trend of more negative tweets up until 2020, both on a regional level and for Norway as a whole. Furthermore, we find weak geographical clustering in our data, indicating that discussions are country wide and not dominated by specific regional events or developments. Twitter data allow for detailed insight into the temporal nature of public sentiments and extending this research to additional case studies of technologies, countries and sources of data (e.g. newspapers, other social media) may prove important to complement traditional survey research and the understanding of public sentiment.

Reducing Loneliness and Improving Social Support among Older Adults through Different Modalities of Personal Voice Assistants.

This study examines the potential of AI-powered personal voice assistants (PVAs) in reducing loneliness and increasing social support among older adults. With the aging population rapidly expanding, innovative solutions are essential. Prior research has indicated the effectiveness of various interactive communication technologies (ICTs) in mitigating loneliness, but studies focusing on PVAs, particularly considering their modality (audio vs. video), are limited. This research aims to fill this gap by evaluating how voice assistants, in both audio and video formats, influence perceived loneliness and social support. This study examined the impact of voice assistant technology (VAT) interventions, both audio-based (A-VAT) and video-based (V-VAT), on perceived loneliness and social support among 34 older adults living alone. Over three months, participants engaged with Amazon Alexa™ PVA through daily routines for at least 30 min. Using a hybrid natural language processing framework, interactions were analyzed. The results showed reductions in loneliness (Z = -2.99, p < 0.01; pre-study loneliness mean = 1.85, SD = 0.61; post-study loneliness mean = 1.65, SD = 0.57), increases in social support post intervention (Z = -2.23, p < 0.05; pre-study social support mean = 5.44, SD = 1.05; post-study loneliness mean = 5.65, SD = 1.20), and a correlation between increased social support and loneliness reduction when the two conditions are combined (ρ = -0.39, p < 0.05). In addition, V-VAT was more effective than A-VAT in reducing loneliness (U = 85.50, p < 0.05) and increasing social support (U = 95, p < 0.05). However, no significant correlation between changes in perceived social support and changes in perceived loneliness was observed in either intervention condition (V-VAT condition: ρ = -0.24, p = 0.37; A-VAT condition: ρ = -0.46, p = 0.06). This study's findings could significantly contribute to developing targeted interventions for improving the well-being of aging adults, addressing a critical global issue.

An NLP Framework for the Extraction of Concept Measurements from Radiology and Pathology Notes.

Natural language processing (NLP) tools can automate the identification of cancer patients eligible for specific pathways. We developed and validated a cancer agnostic, rules-based NLP framework to extract the dimensions and measurements of several concepts from pathology and radiology reports. This framework was then efficiently and cost-effectively deployed to identify patients eligible for breast, lung, and prostate cancers clinical pathways.

The Impact of Turkish Economic News on the Fractality of Borsa Istanbul: A Multidisciplinary Approach

This study explores the connection between the fractal dimensions of time series representing sentiments regarding economic news and the fractal dimensions of correlation networks among companies listed in the Borsa Istanbul star section. While there have been many studies on the correlation between different time series, the investigation into the impact of fractal dimensions on correlation networks’ dynamics has been somewhat restricted. This study investigates the correlation networks among companies listed in the Borsa Istanbul Stars segment, employing distance and topological filters. The network fractional dimensions are evaluated using the box counting and information dimension techniques. A convolutional neural network is employed to perform analysis of sentiments regarding on 2020 Turkish economic news. The network is trained on user comments and specifically built to identify fluctuations in news editorials. The Zemberek natural language processing framework is beneficial for data preprocessing. Identical analytical methods are employed to quantify the fractal dimensions of each sentiment time series. Experiments are performed on these measurements using various sliding window widths to ascertain both independence and causality. The findings indicate a substantial correlation between market behavior and the feelings expressed in economic news.

ChatReview: A ChatGPT-enabled natural language processing framework to study domain-specific user reviews

Intelligent search engines including pre-trained generative transformers (GPT) have revolutionized the user search experience. Several fields including e-commerce, education, and hospitality are increasingly exploring GPT tools to study user reviews and gain critical insights to improve their service quality. However, massive user-review data and imprecise prompt engineering lead to biased, irrelevant, and impersonal search results. In addition, exposing user data to these search engines may pose privacy issues. Motivated by these factors, we present ChatReview, a ChatGPT-enabled natural language processing (NLP) framework that effectively studies domain-specific user reviews to offer relevant and personalized search results at multiple levels of granularity. The framework accomplishes this task using four phases including data collection, tokenization, query construction, and response generation. The data collection phase involves gathering domain-specific user reviews from public and private repositories. In the tokenization phase, ChatReview applies sentiment analysis to extract keywords and categorize them into various sentiment classes. This process creates a token repository that best describes the user sentiments for a given user-review data. In the query construction phase, the framework uses the token repository and domain knowledge to construct three types of ChatGPT prompts including explicit, implicit, and creative. In the response generation phase, ChatReview pipelines these prompts into ChatGPT to generate search results at varying levels of granularity. We analyze our framework using three real-world domains including education, local restaurants, and hospitality. We assert that our framework simplifies prompt engineering for general users to produce effective results while minimizing the exposure of sensitive user data to search engines. We also present a one-of-a-kind Large Language Model (LLM) peer assessment of the ChatReview framework. Specifically, we employ Google’s Bard to objectively and qualitatively analyze the various ChatReview outputs. Our Bard-based analyses yield over 90% satisfaction, establishing ChatReview as a viable survey analysis tool.

BERT-based tourism named entity recognition: making use of social media for travel recommendations.

Social media has become a massive encyclopedia of almost anything due to its content richness. People tell stories, write comments and feedback, and share knowledge through social media. The information available on social media enables 'clueless' travelers to get quick travel recommendations in the tourism sector. Through a simple query, such as typing 'places to visit in Bali', travelers can get many blog articles to help them decide which places of interest to visit. However, doing this reading task without a helper can be overwhelming. To overcome this problem, we developed Bidirectional Encoder Representations from Transformers (BERT)-based tourism named entity recognition system, which is used to highlight tourist destination places in the query result. BERT is a state-of-the-art machine learning framework for natural language processing that can give a decent performance in various settings and cases. Our developed tourism named entity recognition (NER) model specifies three different tourist destinations: heritage, natural, and purposefully built (man-made or artificial). The dataset is taken from various tourism-related community articles and posts. The model achieved an average F1-score of 0.80 and has been implemented into a traveling destination recommendation system. By using this system, travelers can get quick recommendations based on the popularity of places visited in the query frame. Based on the survey that we conducted to target respondents who have never visited and have no or limited knowledge about tourist attractions in some example cities, their average interest level from the recommendation results is higher than four on a scale of 1 to 5. Thus, it can be considered a good recommendation. Furthermore, the NER model performance is comparable to another related research.

Discovering social determinants of health from case reports using natural language processing: algorithmic development and validation

BackgroundSocial determinants of health are non-medical factors that influence health outcomes (SDOH). There is a wealth of SDOH information available in electronic health records, clinical reports, and social media data, usually in free text format. Extracting key information from free text poses a significant challenge and necessitates the use of natural language processing (NLP) techniques to extract key information.ObjectiveThe objective of this research is to advance the automatic extraction of SDOH from clinical texts.Setting and dataThe case reports of COVID-19 patients from the published literature are curated to create a corpus. A portion of the data is annotated by experts to create ground truth labels, and semi-supervised learning method is used for corpus re-annotation.MethodsAn NLP framework is developed and tested to extract SDOH from the free texts. A two-way evaluation method is used to assess the quantity and quality of the methods.ResultsThe proposed NER implementation achieves an accuracy (F1-score) of 92.98% on our test set and generalizes well on benchmark data. A careful analysis of case examples demonstrates the superiority of the proposed approach in correctly classifying the named entities.ConclusionsNLP can be used to extract key information, such as SDOH factors from free texts. A more accurate understanding of SDOH is needed to further improve healthcare outcomes.

Consumer-Perceived Risks and Sustainable Development of China’s Online Gaming Market: Analysis Based on Social Media Comments

Online gaming constitutes an indispensable facet of China’s digital economy, catalyzing consumer discussions on social media platforms. This study employs a comprehensive natural language processing framework, encompassing topic mining, multi-label classification, and sentiment analysis, to evaluate consumers’ psychological perceptions of the risks associated with online games through social media comments. This study identifies 11 distinct perceived risk topics, including “Excessive Temptation”, “Entry Regulation”, and “Culture Implantation”. Numerous comments encompass multiple topics, each infused with diverse emotional inclinations, thus unveiling disparate consumer perspectives. These findings underscore the critical significance of addressing potential perceived risks and mitigating negative consumer emotions for enterprises operating within online gaming. Such measures are pivotal to maintaining a brand image, business reputation, and enduring growth. Furthermore, this study extends valuable insights to regulatory bodies, contributing to enhancing administrative efficiency, safeguarding consumer rights, and fostering a robust and sustainable trajectory within China’s online gaming market.

An open natural language processing (NLP) framework for EHR-based clinical research: a case demonstration using the National COVID Cohort Collaborative (N3C).

Despite recent methodology advancements in clinical natural language processing (NLP), the adoption of clinical NLP models within the translational research community remains hindered by process heterogeneity and human factor variations. Concurrently, these factors also dramatically increase the difficulty in developing NLP models in multi-site settings, which is necessary for algorithm robustness and generalizability. Here, we reported on our experience developing an NLP solution for Coronavirus Disease 2019 (COVID-19) signs and symptom extraction in an open NLP framework from a subset of sites participating in the National COVID Cohort (N3C). We then empirically highlight the benefits of multi-site data for both symbolic and statistical methods, as well as highlight the need for federated annotation and evaluation to resolve several pitfalls encountered in the course of these efforts.

A framework for multi-faceted content analysis of social media chatter regarding non-medical use of prescription medications

BackgroundSubstance use, including the non-medical use of prescription medications, is a global health problem resulting in hundreds of thousands of overdose deaths and other health problems. Social media has emerged as a potent source of information for studying substance use-related behaviours and their consequences. Mining large-scale social media data on the topic requires the development of natural language processing (NLP) and machine learning frameworks customized for this problem. Our objective in this research is to develop a framework for conducting a content analysis of Twitter chatter about the non-medical use of a set of prescription medications.MethodsWe collected Twitter data for four medications—fentanyl and morphine (opioids), alprazolam (benzodiazepine), and Adderall® (stimulant), and identified posts that indicated non-medical use using an automatic machine learning classifier. In our NLP framework, we applied supervised named entity recognition (NER) to identify other substances mentioned, symptoms, and adverse events. We applied unsupervised topic modelling to identify latent topics associated with the chatter for each medication.ResultsThe quantitative analysis demonstrated the performance of the proposed NER approach in identifying substance-related entities from data with a high degree of accuracy compared to the baseline methods. The performance evaluation of the topic modelling was also notable. The qualitative analysis revealed knowledge about the use, non-medical use, and side effects of these medications in individuals and communities.ConclusionsNLP-based analyses of Twitter chatter associated with prescription medications belonging to different categories provide multi-faceted insights about their use and consequences. Our developed framework can be applied to chatter about other substances. Further research can validate the predictive value of this information on the prevention, assessment, and management of these disorders.

CTHP: Selection for adoption of open‐source bioinformatics software based on a customised ISO 25010 quality model, three‐way decision and Delphi hierarchy process

AbstractThe ever‐growing open‐source software tools in different domains increase the difficulty of software selection from the end‐users perspective. The process of evaluating, comparing, and selecting open‐source solutions is far from trivial. Especially, when additional requirements need to be considered, the existing methodologies will fail to adapt to the new tasks. The objective of this study is to present a solution for dealing with this issue. A novel approach, CTHP, is presented for the evaluation and selection of open‐source software in the Bioinformatics domain. First, the ISO 25010 quality model is chosen as the basis. This model is customised according to the special characteristics of the Bioinformatics applications. The customisation is done by extracting the quality factors from the Bioinformatics applications, weighting these factors from the viewpoints of both developers and end‐users, and adding them to the model. After that, Three‐way Decision and Delphi Hierarchy Process are integrated to assist in the selection for adoption. Finally, as a case study, the proposed approach is applied to assist the decision‐making process of two popular natural language processing frameworks in the Bioinformatics area. Our study is a valuable contribution since it provides a systematic way to document the decision‐making process and help the researchers and practitioners of Bioinformatics to make better decisions among the alternatives.

Real-world evidence analysis of early-stage prostate cancer using natural language processing.

e17007 Background: Real-world evidence (RWE) on the epidemiology and management of localized/locally advanced prostate cancer (LPC) is lacking. Here we used EHRead, a natural language processing framework based on SNOMED CT terminology, to extract clinical information from electronic health records (EHRs) to perform a comprehensive description of a real-world cohort of LPC patients. Here we present a follow-up of the project already communicated at ESMO 2020. Methods: This is an observational, multicenter, retrospective study based on the secondary analysis of free-text and structured clinical information found in EHRs from all observed adult patients with LPC between January 2014 and December 2018 in 12 Spanish hospitals. A total of 375 variables were extracted using EHRead to assess patient clinical characteristics, treatment patterns and journey across different prostate cancer stages. Event-free survival (EFS) was analyzed in incident LPC patients with presence of Gleason or PSA and follow-up greater than 0 days. A multivariable Cox-proportional hazards model was applied to obtain adjusted hazard ratios (aHR). Results: We observed 19788 patients with LPC during a median of 3.5 (interquartile range 1.4-7.4) years of follow-up. 52% of patients had low- (LR), 21% intermediate- (IR) and 27% high-risk (HR) disease. 3938 (18%) patients transitioned to other disease stages, leading to castration-resistant prostate cancer (mCRPC) in 4%, 7%, 16% of patients with LR, IR, and HR LPC, respectively. 7884 (42%) patients received radiotherapy (RT), 7021 (38%) prostatectomy (PT), 6061 (31%) androgen deprivation therapy (ADT), and 1034 (6%) active surveillance. Local recurrence was observed in 3% and distant metastasis in 11% (57% bone, 37% visceral). Distant metastases were observed in 7%, 12% and 21% of HR, IR and LR; 8% vs. 9% of PT vs. RT; and 16% vs 6% of ADT vs. no ADT, respectively. EFS was assessed in 7465 (38%) patients, with a 4-year EFS rate of 18%. Median EFS was 22, 13, and 8 months for LR, IR, HR; 23 vs. 12 months for PT vs. RT; and 8 vs. 21 months for ADT vs. no ADT, respectively. A multivariable cox proportional hazards model is presented in the following Table. Conclusions: During the study period, 11% of all LPC patients developed metastatic disease, with only 18% remaining event-free at 4 years. Transition to mCRPC was 4- and 2-fold higher in HR vs. IR and LR disease, respectively. Disease risk, treatment with RT and/or addition of ADT were independently associated with shorter EFS. Our findings suggest that, despite adjuvant treatment, LPC local extension and histopathological characteristics at diagnosis remain critical determinants of patient prognosis. A more detailed analysis in patients with available Gleason and PSA is underway. [Table: see text]

A natural language processing framework for analyzing public transportation user satisfaction: a case study

Public transportation services make an important contribution to the nation's economy. However, the public transportation system was significantly impacted both during and after the Covid-19 outbreak. To minimize these impacts, it is important to know the users' sentiment and improve the service quality accordingly to change the users' attitude towards public transportation systems. Natural language processing is used to make meaningful inferences about user sentiment using various analysis techniques. Historically, surveys have also been used for years to learn users' opinions about transportation services. In this study, this traditional method was used to determine the satisfaction of public transportation users. The categorization model employed in the system developed as part of this work is based on algorithms such as Long Short-Term Memory (LSTM), Random Forest (RF), and Multi Logistic Regression (MLR). The dataset contains information gathered from the online survey. Of the models created utilizing the training dataset, it was discovered that the LSTM model offered the highest accuracy. Users' comments can help improve public transportation operators' operations, improve service quality, and monitor actions accordingly. Therefore, in this study, users' emotions were classified as positive, negative, or neutral based on the comments.

A rationale-augmented NLP framework to identify unilateral contractual change risk for construction projects

Construction projects often see owners who exert their dominance by modifying the standard contracts without contractors’ prior consent. This can lead to undesirable outcomes for contractors, thus referred to as unilateral contractual change risk (UCCR) in this study. As such, identifying UCCR proactively becomes essential for contractors, particularly in engineering-procurement-construction (EPC) projects where the claim scope is limited. Although natural language processing (NLP) has shown promise in the identification of UCCR, it faces difficulties due to the high cognitive demands required. To fill the gap, we propose a rational-augmented NLP framework that emulates human reasoning to identify UCCR in EPC contracts in an explainable and effective manner. The framework (1) leverages NLP techniques to disassemble contract text into features that draw the attention of human readers for obligation-related comprehension, and (2) generates a coherent sequence of intermediate reasoning steps using a customized Microsoft Excel and-in interface to identify predetermined categories of UCCR. Our framework, which achieves an outstanding F1 score of 0.87, is trained on a widely used standard form of EPC contract. It also presents a user-friendly interface for contractors to discern any intentional or malicious acts committed by the owner during the contract stage. Furthermore, our methodology can be adapted to enhance risk management in other sectors.

From Twitter to Aso-Rock: A sentiment analysis framework for understanding Nigeria 2023 presidential election

IntroductionSocial media platforms such as Facebook, LinkedIn, Twitter, among others have been used as tools for staging protests, opinion polls, campaign strategy, medium of agitation and a place of interest expression especially during elections. AimIn this work, a Natural Language Processing framework is designed to understand Nigeria 2023 presidential election based on public opinion using Twitter dataset. MethodsTwo million tweets with 18 features were collected from Twitter containing public and personal tweets of the three top contestants – Atiku Abubakar, Peter Obi and Bola Tinubu – in the forthcoming 2023 Presidential election. Sentiment analysis was performed on the preprocessed dataset using three machine learning models namely: Long Short-Term Memory (LSTM) Recurrent Neural Network, Bidirectional Encoder Representations from Transformers (BERT) and Linear Support Vector Classifier (LSVC) models. This study spanned ten weeks starting from the candidates’ declaration of intent to run for Presidency. ResultsThe sentiment models gave an accuracy, precision, recall, AUC and f-measure of 88%, 82.7%, 87.2%, 87.6% and 82.9% respectively for LSTM; 94%, 88.5%, 92.5%, 94.7% and 91.7% respectively for BERT and 73%, 81.4%, 76.4%, 81.2% and 79.2% respectively for LSVC. Result also showed that Peter Obi has the highest total impressions the highest positive sentiments, Tinubu has the highest network of active friends while Atiku has the highest number of followers. ConclusionSentiment analysis and other Natural Language Understanding tasks can aid in the understanding of the social media space in terms of public opinion mining. We conclude that opinion mining from Twitter can form a general basis for generating insights for election as well as modeling election outcomes.