Natural Language Processing Models Research Articles

Enhancing ESL Students’ Writing Skills through Natural Language Processing Model Chat GPT

This research paper describes an experimental study to determine the effectiveness of using Chat GPT based natural language processing (NLP) model to improve the writing proficiency of ESL students. The study shows how such approach can be integrated into the teaching process to improve the quality of writing skills. The paper provides an overview of methods of teaching writing according to certain criteria for assessing writing skills. The effectiveness of the model is assessed in comparison with traditional teaching methods. Recommendations are given for optimizing the learning process using NLP technologies. The conclusion highlights the significance of the technology used in improving writing skills and discusses the prospects for using the Chat GPT model to optimize these skills in ESL students.

The BioRECIPE Knowledge Representation Format.

The BioRECIPE (Biological system Representation for Evaluation, Curation, Interoperability, Preserving, and Execution) knowledge representation format was introduced to standardize and facilitate human-machine interaction while creating, verifying, evaluating, curating, and expanding executable models of intra- and intercellular signaling. This format allows a human user to easily preview and modify any model component, while it is at the same time readable by machines and can be processed by a suite of model development and analysis tools. The BioRECIPE format is compatible with multiple representation formats, natural language processing tools, modeling tools, and databases that are used by the systems and synthetic biology communities.

Text Summarization in the Shona Language using Natural Language Processing

The rise of digital information in many languages, including Shona, highlights the significance of developing effective text summarizing techniques to promote information accessibility and usability. This work fills a major gap in the natural language processing (NLP) for the Shona language, which is widely spoken in Zimbabwe and its surrounding areas but has received little attention. The lack of pre-trained language models specifically designed for Shona, the intricacy of Shona's morphology, and the scarcity of annotated datasets provide the main obstacles to Shona text summarization.[1] The goal of this research is to create and modify contemporary machine learning methods for efficient Shona text summarizing in order to address these issues. By gathering and analyzing texts from a variety of sources, such as news stories, scholarly papers, and social media, we produced large annotated corpora. These datasets were utilized to fine-tune existing NLP models, such as Transformer-based architectures, ensuring they account for Shona’s specific language traits. To address the morphological and syntactic complexities of Shona, our solution combines statistical and rule-based techniques. When compared to baseline methods, the results show a significant improvement in the relevancy and accuracy of Shona text summaries. In addition to serving as a starting point for further NLP research in underrepresented languages, the generated models help Shona-speaking people in the areas of business, education, and media. By encouraging inclusivity and linguistic variety, showcasing the possibility for cross- lingual breakthroughs, and emphasizing the ethical development of technology, this research adds to the larger area of NLP.

Utilizing Large Language Models to Illustrate Constraints for Construction Planning

Effective construction project planning relies on addressing constraints related to materials, labor, equipment, and others. Planning meetings are typical venues for stakeholders to identify, communicate, and remove constraints. However, a critical gap exists in lacking an automated approach to identify, classify, analyze, and track constraint discussions during onsite planning meetings. Therefore, this research aims to 1. develop a natural language processing model to classify constraints in meeting discussions; 2. uncover the discussion patterns of managers and foremen regarding various constraints; and 3. extract the root causes for constraints, evaluate their impacts, and prepare managers to develop practical solutions for constraint removal. This research collected meeting transcripts from 94 onsite planning meetings of a building project, spanning 263,836 words. Next, this research leveraged a general pretrained transformer (GPT) to segment discussion dialogs into topics. A Bidirectional Encoder Representations from Transformers (BERT)-based model was developed to categorize constraint types for each topic. The constraint patterns among meeting attendees were assessed. Furthermore, a GPT-based tool was devised to track root causes, impacts, and solutions for various constraints. Test results revealed an 8.8% improvement in constraint classification accuracy compared with the traditional classification model. An occupational characteristic in constraint discussion was observed in that the management team tended to balance their focus on various constraints, while foremen concentrated on more practical issues. This research contributes to the body of knowledge by leveraging language models to analyze construction planning meetings. The findings facilitate project managers in establishing constraint logs for diagnosing and prognosticating planning issues.

Evaluating large language models for health-related text classification tasks with public social media data.

Large language models (LLMs) have demonstrated remarkable success in natural language processing (NLP) tasks. This study aimed to evaluate their performances on social media-based health-related text classification tasks. We benchmarked 1 Support Vector Machine (SVM), 3 supervised pretrained language models (PLMs), and 2 LLMs-based classifiers across 6 text classification tasks. We developed 3 approaches for leveraging LLMs: employing LLMs as zero-shot classifiers, using LLMs as data annotators, and utilizing LLMs with few-shot examples for data augmentation. Across all tasks, the mean (SD) F1 score differences for RoBERTa, BERTweet, and SocBERT trained on human-annotated data were 0.24 (±0.10), 0.25 (±0.11), and 0.23 (±0.11), respectively, compared to those trained on the data annotated using GPT3.5, and were 0.16 (±0.07), 0.16 (±0.08), and 0.14 (±0.08) using GPT4, respectively. The GPT3.5 and GPT4 zero-shot classifiers outperformed SVMs in a single task and in 5 out of 6 tasks, respectively. When leveraging LLMs for data augmentation, the RoBERTa models trained on GPT4-augmented data demonstrated superior or comparable performance compared to those trained on human-annotated data alone. The results revealed that using LLM-annotated data only for training supervised classification models was ineffective. However, employing the LLM as a zero-shot classifier exhibited the potential to outperform traditional SVM models and achieved a higher recall than the advanced transformer-based model RoBERTa. Additionally, our results indicated that utilizing GPT3.5 for data augmentation could potentially harm model performance. In contrast, data augmentation with GPT4 demonstrated improved model performances, showcasing the potential of LLMs in reducing the need for extensive training data. By leveraging the data augmentation strategy, we can harness the power of LLMs to develop smaller, more effective domain-specific NLP models. Using LLM-annotated data without human guidance for training lightweight supervised classification models is an ineffective strategy. However, LLM, as a zero-shot classifier, shows promise in excluding false negatives and potentially reducing the human effort required for data annotation.

Does gender impact the relationship between perceived value and intentions of use of natural processing models?

Purpose In the era of artificial intelligence, natural language processing (NLP) models are revolutionizing numerous sectors. This research aims to explore the perceived value of them among university students. In particular, it aims to investigate how gender may influence students’ intention to use these models in educational contexts, highlighting potentially significant differences that could inform the implementation and adoption of educational technologies. Design/methodology/approach This study investigates the relationship between perceived value and students' intention to adopt NLP models, considering gender as a moderator. The research involves 562 students from the University of Salerno, in Italy, and uses confirmatory factor analysis to evaluate the reliability and validity of the measurement scales. A regression model with robust errors is used to explore the moderating role of gender on the relationship between perceived value and intentions of use of NLP models. Findings The results reveal a significant positive association between perceived value and intention to use NLP models, confirming that students with higher perceived value are more likely to adopt these technologies. Furthermore, gender moderates this relationship, indicating that females are less prone to use NLP models than male counterparts. Originality/value Research takes on a significant role in the academic field, underlining the importance of adapting teaching practices to the increasingly widespread digitalization. The inclusion of NLP models in university programs emerges as a possible improvement of the learning experience, ensuring cutting-edge education in tune with the needs of the digital society.

Information retrieval and classification of real-time multi-source hurricane evacuation notices

In the United States, tracking time-sensitive critical information such as evacuation notices for approaching natural hazards like hurricanes poses a significant challenge. This difficulty arises from the rapid issuing and distribution of these notices by numerous local authorities that may span multiple states. Additionally, evacuation notices often undergo frequent updates, and they are distributed through various online portals lacking standard formats. Unlike weather warnings, there is no centralized database for live (or past) evacuation notices. To meet the demand of data for crisis-related government notices, we developed an approach to detect and retrieve locally issued hurricane evacuation notices in real time. Evacuation-related text data were collected mainly through spatially targeted information retrieval. These data were then manually labeled and used to train natural language processing (NLP) models. The NLP models in turn classified all text data into one of the three notice categories, i.e., mandatory evacuation notices, voluntary evacuation notices, and not an evacuation notice. The classification of mandatory evacuation notices achieved a very high accuracy (recall = 96 %). These NLP models, when applied to future hurricanes, will provide real-time evacuation notices for situation awareness to higher-level government agencies and news outlets. The archived evacuation notices serve as a valuable resource for scholars to study government responses to weather warnings and individual behaviors influenced by evacuation history. Our research framework may extend to other disaster types, allowing for rapid and targeted retrieval, classification, redistribution, and archiving of real-time government orders and notifications.

Artificial intelligence for hearing loss prevention, diagnosis, and management

This paper explores the transformative impact of artificial intelligence (AI), particularly machine learning (ML), on diagnosing and treating hearing loss, which affects over 5% of the global population across all ages and demographics. AI encompasses various applications, from natural language processing models like ChatGPT to image recognition systems; however, this paper focuses on ML, a subfield of AI that can revolutionize audiology by enhancing early detection, formulating personalized rehabilitation plans, and integrating electronic health records for streamlined patient care. The integration of ML into audiometry, termed "computational audiology," allows for automated, accurate hearing tests. AI algorithms can process vast data sets, provide detailed audiograms, and facilitate early detection of hearing impairments. Research shows ML's effectiveness in classifying audiograms, conducting automated audiometry, and predicting hearing loss based on noise exposure and genetics. These advancements suggest that AI can make audiological diagnostics and treatment more accessible and efficient. The future of audiology lies in the seamless integration of AI technologies. Collaborative efforts between audiologists, AI experts, and individuals with hearing loss are essential to overcome challenges and leverage AI's full potential. Continued research and development will enhance AI applications in audiology, improving patient outcomes and quality of life worldwide.

Natural Language Processing Accurately Differentiates Cancer Symptom Information in Electronic Health Record Narratives.

Identifying cancer symptoms in electronic health record (EHR) narratives is feasible with natural language processing (NLP). However, more efficient NLP systems are needed to detect various symptoms and distinguish observed symptoms from negated symptoms and medication-related side effects. We evaluated the accuracy of NLP in (1) detecting 14 symptom groups (ie, pain, fatigue, swelling, depressed mood, anxiety, nausea/vomiting, pruritus, headache, shortness of breath, constipation, numbness/tingling, decreased appetite, impaired memory, disturbed sleep) and (2) distinguishing observed symptoms in EHR narratives among patients with cancer. We extracted 902,508 notes for 11,784 unique patients diagnosed with cancer and developed a gold standard corpus of 1,112 notes labeled for presence or absence of 14 symptom groups. We trained an embeddings-augmented NLP system integrating human and machine intelligence and conventional machine learning algorithms. NLP metrics were calculated on a gold standard corpus subset for testing. The interannotator agreement for labeling the gold standard corpus was excellent at 92%. The embeddings-augmented NLP model achieved the best performance (F1 score = 0.877). The highest NLP accuracy was observed in pruritus (F1 score = 0.937) while the lowest accuracy was in swelling (F1 score = 0.787). After classifying the entire data set with embeddings-augmented NLP, we found that 41% of the notes included symptom documentation. Pain was the most documented symptom (29% of all notes) while impaired memory was the least documented (0.7% of all notes). We illustrated the feasibility of detecting 14 symptom groups in EHR narratives and showed that an embeddings-augmented NLP system outperforms conventional machine learning algorithms in detecting symptom information and differentiating observed symptoms from negated symptoms and medication-related side effects.

Community-engaged artificial intelligence research: A scoping review.

The degree to which artificial intelligence healthcare research is informed by data and stakeholders from community settings has not been previously described. As communities are the principal location of healthcare delivery, engaging them could represent an important opportunity to improve scientific quality. This scoping review systematically maps what is known and unknown about community-engaged artificial intelligence research and identifies opportunities to optimize the generalizability of these applications through involvement of community stakeholders and data throughout model development, validation, and implementation. Embase, PubMed, and MEDLINE databases were searched for articles describing artificial intelligence or machine learning healthcare applications with community involvement in model development, validation, or implementation. Model architecture and performance, the nature of community engagement, and barriers or facilitators to community engagement were reported according to PRISMA extension for Scoping Reviews guidelines. Of approximately 10,880 articles describing artificial intelligence healthcare applications, 21 (0.2%) described community involvement. All articles derived data from community settings, most commonly by leveraging existing datasets and sources that included community subjects, and often bolstered by internet-based data acquisition and subject recruitment. Only one article described inclusion of community stakeholders in designing an application-a natural language processing model that detected cases of likely child abuse with 90% accuracy using harmonized electronic health record notes from both hospital and community practice settings. The primary barrier to including community-derived data was small sample sizes, which may have affected 11 of the 21 studies (53%), introducing substantial risk for overfitting that threatens generalizability. Community engagement in artificial intelligence healthcare application development, validation, or implementation is rare. As healthcare delivery occurs primarily in community settings, investigators should consider engaging community stakeholders in user-centered design, usability, and clinical implementation studies to optimize generalizability.

Language or rating scales based classifications of emotions: computational analysis of language and alexithymia

Rating scales are the dominating tool for the quantitative assessment of mental health. They are often believed to have a higher validity than language-based responses, which are the natural way of communicating mental states. Furthermore, it is unclear how difficulties articulating emotions—alexithymia—affect the accuracy of language-based communication of emotions. We investigated whether narratives describing emotional states are more accurately classified by questions-based computational analysis of language (QCLA) compared to commonly used rating scales. Additionally, we examined how this is affected by alexithymia. In Phase 1, participants (N = 348) generated narratives describing events related to depression, anxiety, satisfaction, and harmony. In Phase 2, another set of participants summarized the emotions described in the narratives of Phase 1 in five descriptive words and rating scales (PHQ-9, GAD-7, SWLS, and HILS). The words were quantified with a natural language processing model (i.e., LSA) and classified with machine learning (i.e., multinomial regression). The results showed that the language-based responses can be more accurate in classifying the emotional states compared to the rating scales. The degree of alexithymia did not influence the correctness of classification based on words or rating scales, suggesting that QCLA is not sensitive to alexithymia. However, narratives generated by people with high alexithymia were more difficult to classify than those generated by people with low alexithymia. These results suggest that the assessment of mental health may be improved by language-based responses analyzed by computational methods compared to currently used rating scales.

ChatGPT Predicts In-Hospital All-Cause Mortality for Sepsis: In-Context Learning with the Korean Sepsis Alliance Database.

Sepsis is a leading global cause of mortality, and predicting its outcomes is vital for improving patient care. This study explored the capabilities of ChatGPT, a state-of-the-art natural language processing model, in predicting in-hospital mortality for sepsis patients. This study utilized data from the Korean Sepsis Alliance (KSA) database, collected between 2019 and 2021, focusing on adult intensive care unit (ICU) patients and aiming to determine whether ChatGPT could predict all-cause mortality after ICU admission at 7 and 30 days. Structured prompts enabled ChatGPT to engage in in-context learning, with the number of patient examples varying from zero to six. The predictive capabilities of ChatGPT-3.5-turbo and ChatGPT-4 were then compared against a gradient boosting model (GBM) using various performance metrics. From the KSA database, 4,786 patients formed the 7-day mortality prediction dataset, of whom 718 died, and 4,025 patients formed the 30-day dataset, with 1,368 deaths. Age and clinical markers (e.g., Sequential Organ Failure Assessment score and lactic acid levels) showed significant differences between survivors and non-survivors in both datasets. For 7-day mortality predictions, the area under the receiver operating characteristic curve (AUROC) was 0.70-0.83 for GPT-4, 0.51-0.70 for GPT-3.5, and 0.79 for GBM. The AUROC for 30-day mortality was 0.51-0.59 for GPT-4, 0.47-0.57 for GPT-3.5, and 0.76 for GBM. Zero-shot predictions using GPT-4 for mortality from ICU admission to day 30 showed AUROCs from the mid-0.60s to 0.75 for GPT-4 and mainly from 0.47 to 0.63 for GPT-3.5. GPT-4 demonstrated potential in predicting short-term in-hospital mortality, although its performance varied across different evaluation metrics.

Adjusting Mood in Mandarin Chinese: A Game Theory Approach to Double and Redundant Negation with Entropy

Abstract This study investigates how Mandarin Chinese speakers use double and redundant negations to adjust information entropy and convey the speaker’s mood. Integrating Gricean implicature, signaling game theory, and information entropy, we quantified uncertainty in negation sentences by calculating self-information of negation markers and overall entropy for negations versus affirmatives. Analyzing sentences from the BCC Corpus of Mandarin Chinese newspapers, we extracted double and redundant negation patterns, calculated their frequencies, and compared entropy values in payoff matrices against affirmatives. Contextual analysis of surrounding discourse interpreted pragmatic functions. Our findings reveal that universal double negations reduce sentence entropy, intensifying assertiveness. Modal forms further decrease entropy, amplifying necessity, while conditional patterns strengthen the asserted conditions. Euphemistic double negations increase entropy, weaken assertiveness, and align with Levinson’s Manner Principle. This increase in entropy quantifies pragmatic markedness, allowing tentative critiques. Redundant negations significantly reduce entropy, strengthening negative attitudes. We elucidate how interlocutors navigate cooperative discourse by quantifying uncertainty via entropy measures, making contextually-optimal linguistic choices like assertion, indirectness, and emphasis. These findings impact signaling game theory and pragmatic markedness, with applications in natural language processing, cross-cultural communication, and computational models. Future research could explore other languages and cognitive and social factors in negation use.

Natural Language Processing (NLP) for Sentiment Analysis in Social Media

Purpose: This study sought to analyze Natural Language Processing (NLP) for sentiment analysis in social media. Methodology: The study adopted a desktop research methodology. Desk research refers to secondary data or that which can be collected without fieldwork. Desk research is basically involved in collecting data from existing resources hence it is often considered a low cost technique as compared to field research, as the main cost is involved in executive’s time, telephone charges and directories. Thus, the study relied on already published studies, reports and statistics. This secondary data was easily accessed through the online journals and library. Findings: The findings reveal that there exists a contextual and methodological gap relating to Natural Language Processing (NLP) for sentiment analysis in social media. Preliminary empirical review revealed that advanced computational techniques significantly advanced the understanding of sentiments across diverse social media platforms. Methodologies such as machine learning algorithms and deep learning models like CNNs and RNNs demonstrated robust capabilities in categorizing sentiments accurately and capturing contextual nuances such as sarcasm and slang. The research highlighted the interdisciplinary nature of NLP applications, integrating linguistics with computer science and social sciences to develop effective frameworks for analyzing large-scale social media data. These findings contributed to enhancing decision-making in marketing, politics, and public opinion research, pointing towards future directions in hybrid NLP models for improved sentiment analysis across different languages and cultural contexts. Unique Contribution to Theory, Practice and Policy: The Social Constructionism, Cognitive Linguistics and Discourse Analysis Theory may be used to anchor future studies on Natural Language Processing (NLP). The recommendations aimed to advance theoretical foundations by exploring deep learning models and nuanced sentiment lexicons. Practical applications were enhanced through the development of scalable NLP tools for real-time data processing and integration into social media platforms. Policy implications focused on establishing ethical guidelines for data privacy and bias mitigation in sentiment analysis algorithms. Cross-disciplinary collaboration fostered innovation by integrating insights from computer science, linguistics, psychology, and social sciences. Education initiatives and international collaborations were prioritized to build capacity and standardize methodologies globally, ensuring advancements in both research and practical deployment of sentiment analysis technologies.

Evaluating automatic annotation of lexicon-based models for stance detection of M-pox tweets from May 1st to Sep 5th, 2022.

Manually labeling data for supervised learning is time and energy consuming; therefore, lexicon-based models such as VADER and TextBlob are used to automatically label data. However, it is argued that automated labels do not have the accuracy required for training an efficient model. Although automated labeling is frequently used for stance detection, automated stance labels have not been properly evaluated, in the previous works. In this work, to assess the accuracy of VADER and TextBlob automated labels for stance analysis, we first manually label a Twitter, now X, dataset related to M-pox stance detection. We then fine-tune different transformer-based models on the hand-labeled M-pox dataset, and compare their accuracy before and after fine-tuning, with the accuracy of automated labeled data. Our results indicated that the fine-tuned models surpassed the accuracy of VADER and TextBlob automated labels by up to 38% and 72.5%, respectively. Topic modeling further shows that fine-tuning diminished the scope of misclassified tweets to specific sub-topics. We conclude that fine-tuning transformer models on hand-labeled data for stance detection, elevates the accuracy to a superior level that is significantly higher than automated stance detection labels. This study verifies that automated stance detection labels are not reliable for sensitive use-cases such as health-related purposes. Manually labeled data is more convenient for developing Natural Language Processing (NLP) models that study and analyze mass opinions and conversations on social media platforms, during crises such as pandemics and epidemics.

Automated Identification of Fall-related Injuries in Unstructured Clinical Notes.

Fall-related injuries (FRIs) are a major cause of hospitalizations among older patients, but identifying them in unstructured clinical notes poses challenges for large-scale research. In this study, we developed and evaluated Natural Language Processing (NLP) models to address this issue. We utilized all available clinical notes from the Mass General Brigham for 2,100 older adults, identifying 154,949 paragraphs of interest through automatic scanning for FRI-related keywords. Two clinical experts directly labeled 5,000 paragraphs to generate benchmark-standard labels, while 3,689 validated patterns were annotated, indirectly labeling 93,157 paragraphs as validated-standard labels. Five NLP models, including vanilla BERT, RoBERTa, Clinical-BERT, Distil-BERT, and SVM, were trained using 2,000 benchmark paragraphs and all validated paragraphs. BERT-based models were trained in three stages: Masked Language Modeling, General Boolean Question Answering (QA), and QA for FRI. For validation, 500 benchmark paragraphs were used, and the remaining 2,500 for testing. Performance metrics (precision, recall, F1 scores, Area Under ROC [AUROC] or Precision-Recall [AUPR] curves) were employed by comparison, with RoBERTa showing the best performance. Precision was 0.90 [0.88-0.91], recall [0.90-0.93], F1 score 0.90 [0.89-0.92], AUROC and AUPR curves of 0.96 [0.95-0.97]. These NLP models accurately identify FRIs from unstructured clinical notes, potentially enhancing clinical notes-based research efficiency.

Applying the Markov chain in natural language processing and three-pool model

This paper delves into the application of Markov chains in Natural Language Processing (NLP), and the Markov Chain Monte Carlo (MCMC) methodology relevant to the three-pool model. The former outlines the basic principles of Markov chains, highlighting their utility in predicting word sequences in language modelling and text generation, despite certain limitations. Also, the former describes mathematical frameworks like n-gram models that enhance prediction accuracy by considering multiple preceding words. It acknowledges challenges in NLP such as oversimplification and emotional depth, as well as computational issues in higher-order models. It concludes by discussing the integration of Markov chains with other models to mitigate these limitations, and their enduring relevance in computational linguistics. The later investigates the MCMC methodology, a seminal development in the field of statistical inference, which is especially useful when analysing complicated systems when traditional statistical techniques are inadequate. Moreover, this later explores the fundamental concepts of MCMC, clarifies how it is inherently related to Markov chains, presents the three-pool model that is commonly applied to models of physical, chemical, or ecological systems, and discusses how MCMC can be used to analyse these models.

Using natural language processing to facilitate the harmonisation of mental health questionnaires: a validation study using real-world data

BackgroundPooling data from different sources will advance mental health research by providing larger sample sizes and allowing cross-study comparisons; however, the heterogeneity in how variables are measured across studies poses a challenge to this process.MethodsThis study explored the potential of using natural language processing (NLP) to harmonise different mental health questionnaires by matching individual questions based on their semantic content. Using the Sentence-BERT model, we calculated the semantic similarity (cosine index) between 741 pairs of questions from five questionnaires. Drawing on data from a representative UK sample of adults (N = 2,058), we calculated a Spearman rank correlation for each of the same pairs of items, and then estimated the correlation between the cosine values and Spearman coefficients. We also used network analysis to explore the model’s ability to uncover structures within the data and metadata.ResultsWe found a moderate overall correlation (r = .48, p < .001) between the two indices. In a holdout sample, the cosine scores predicted the real-world correlations with a small degree of error (MAE = 0.05, MedAE = 0.04, RMSE = 0.064) suggesting the utility of NLP in identifying similar items for cross-study data pooling. Our NLP model could detect more complex patterns in our data, however it required manual rules to decide which edges to include in the network.ConclusionsThis research shows that it is possible to quantify the semantic similarity between pairs of questionnaire items from their meta-data, and these similarity indices correlate with how participants would answer the same two items. This highlights the potential of NLP to facilitate cross-study data pooling in mental health research. Nevertheless, researchers are cautioned to verify the psychometric equivalence of matched items.

How artificial intelligence can enable data classification for market sizing - Insights from applications in practice

Determining the size of the addressable market is a key aspect of market intelligence and requires identifying and delineating projected budget data from potential customers. The market intelligence arena is characterized by a wide range of disparate sources, many of which are unstructured, ranging across competitive, market, financial, and technology sources, and typically necessitating significant manual work to analyze, reconcile, and integrate. The authors present an approach for classification of data from one of these sources, facilitating aggregation and analysis of intelligence information. We describe a concept proof using machine learning that extends a model for automatic mapping of publicly available budget data to segments and subsegments of a market segmentation taxonomy. This approach automates the tagging of market and market segment for each program and cost element by training classification models on the manually labeled historical data. We describe the evaluation and use of multiple natural language processing (NLP) and classification modeling methods. This work's contribution is demonstrating how NLP and machine learning techniques can provide useful data classification and automatic classification even when source data diverges from its specified taxonomic description.

A Natural Language Processing Model for Automated Organization and Analysis of Intangible Cultural Heritage

This paper investigates text similarity methods in the field of NLP, improves upon the WMD, and develops the SWC-WMD distance, forming the basis for a clustering method for long ICH texts. Clustering experiments on the constructed ICH long text dataset using WMD, SWC-WMD, and TF-IDF-WMD distances were conducted. The impact of the number of feature words on clustering results and the effect of different distances on clustering outcomes were assessed based on accuracy and F1 values from the evaluation criteria. The final results show that the SWC-WMD distance improves the accuracy and F1 values of the ICH long text clustering results compared to the other two distances, thereby proving the effectiveness of the methods proposed in this paper.