Artificial Intelligence Natural Language Processing Research Articles

Exploring knowledge management technologies to enhance sustainability and mitigate technostress from a collaborative perspective

Purpose The relevance of digital technology and knowledge management (KM) has been increasing continuously owing to their importance in sustainability. However, research on which technology leads to collaboration in KM and how it affects sustainability is lacking. Therefore, this study aims to analyze knowledge collaboration management technologies for sustainable growth based on academic literature and technology patents. Design/methodology/approach This paper analyzed current technology and academic trends in KM using BERTopic, an artificial intelligence natural language processing model, and proposed future promising candidate technologies and potential application areas in terms of collaboration and sustainability. Findings From the textual data of research papers and patents, this paper extracted 10 and 47 major topics, respectively. Moreover, five potential and feasible candidate patents along with their applicable fields were recommended. Originality/value The strength of this study is its analysis of the technologies affecting collaboration and sustainability in KM. This paper found that new digital technologies (i.e. artificial intelligence, cloud computing and big data) impact organizations’ KM and have the potential for collaboration. Digital technologies have a positive impact on corporate smartness directly and sustainability and inclusion indirectly. This paper argued that organizations should understand and identify various promising technological factors and apply them to their KM from a collaboration perspective.

Artificial Intelligence: An Experiential Learning Tool to Acquire Knowledge and Enhance Creativity

Higher education students are recognized for neglecting assigned readings hence, researchers explored artificial intelligence (AI) as an instrument of motivation; in the quest to satisfy this demand, another interference developed, English, a linguistic barrier. Multi-cultural disparities impede literacy, equally, AI natural language processing (NLP) and prompts require fluency and command of English, which can be a hindrance for the underprivileged. The research aimed to determine the potential of AI educational tools in facilitating learning. Empirically, exploratory design was espoused to uncover the reasons behind college students’ lack of interest in reading and identify factors that can motivate them. One hundred and sixty-two first-year college students participated in the study, in November 2023. AI was specifically selected as a motivational instrument. Findings show students expressed optimism regarding the integration of AI into education, high-achieving students displayed confidence when interacting with AI, while those with lower proficiency faced difficulties due to NLP obstacles.

Shareable artificial intelligence to extract cancer outcomes from electronic health records.

11000 Background: Clinical outcomes such as response, progression, and metastasis represent crucial data for observational cancer research, but outside of clinical trials, such outcomes are usually recorded only in unstructured notes in electronic health records (EHRs). Manual EHR annotation is too resource-intensive to scale to large datasets. Individual cancer centers have trained artificial intelligence natural language processing (AI/NLP) models to extract outcomes from their EHRs. However, due to concerns that models trained on protected health information (PHI) might encode private data, such models usually cannot be exported to other centers. Methods: EHR data from Dana-Farber Cancer Institute (DFCI) and Memorial-Sloan Kettering (MSK) collected through the AACR Project GENIE Biopharma Collaborative were used to train and evaluate Bidirectional Encoder Representations from Transformers (BERT)-based NLP models to extract outcomes from imaging reports and oncologist notes annotated with the Pathology, Radiology/Imaging, Signs/Symptoms, Medical oncologist, and bioMarkers (PRISSMM) framework. Document-level outcomes included the presence of active cancer; response; progression; and metastatic sites. ‘Teacher’ models trained on DFCI EHR data were used to label imaging reports and discharge summaries from the public MIMIC-IV dataset. ‘Student’ models trained to use MIMIC documents to predict teacher labels were transferred to MSK for evaluation. Results: Teacher models were trained at DFCI on 30,332 imaging reports for 2609 patients and 32,173 oncologist notes for 2917 patients with non-small cell lung, colorectal, breast, prostate, pancreatic, or urothelial cancer. The models were used to label 217,642 imaging reports and 141,377 discharge summaries from MIMIC for student model training. These DFCI-trained student models were evaluated at MSK, demonstrating high discrimination (AUROC > 0.90) across outcomes. Conclusions: This privacy-preserving “teacher-student” AI/NLP framework could expedite linkage of genomic data to clinical outcomes across institutions, accelerating precision cancer research. [Table: see text]

Artificial Intelligence-Powered Sentiment Analysis of Water Births on YouTube via ChatGPT [ID 2683505

INTRODUCTION: YouTube is a popular platform for sharing information regarding experiences during pregnancy, including water births. Thus, it is beneficial for health care providers to be aware of the sentiment towards water birth in the most popular videos on the topic. ChatGPT, an artificial intelligence natural language processing tool was utilized to assess sentiments expressed by pregnant individuals and their loved ones through YouTube videos. METHODS: A YouTube search query on “water birth” was conducted. English transcripts from the top 100 “most viewed” videos were extracted and analyzed using ChatGPT, which categorized sentiments as positive, negative, neutral, or mixed. Chi-squared goodness-of-fit and independence tests were performed to assess significance of differences between groups. RESULTS: Of the 63 YouTube videos that met criteria, 52.4% were positive, 17.5% were mixed, 15.9% could not be assessed, 12.7% were neutral, and 1.6% were negative (P<.0001). Videos were uploaded from North America (84%), Australia (5%), Europe (5%), Asia (4%), Africa (1%), and South America (1%). When comparing North America to other regions, results are as follows: positive (54.7% versus 50% [P=.3173]), negative (8% versus 0% [P=.0032]), neutral (17.2% versus 16.7% [P=.6716]), and mixed (9.4% versus 8.3% [P=.2074]). CONCLUSION: As the trend of sharing labor and delivery experiences online gains traction, it is important to understand the sentiment surrounding water births on social media platforms such as YouTube. Over half of all sentiments on water birth were positive, whereas only a small amount were found to have a negative sentiment. While a majority of the most popular videos on water births are from North America, it is important to note that North American videos expressed more negative sentiment compared to other continents. Ongoing efforts should be undertaken to gain insights into the sentiments associated with nontraditional labor and delivery methods.

Classification of comments on social media based on long short-term memory

Social media has assumed a pivotal role in contemporary society, significantly enhancing the convenience of daily lives. Nonetheless, the prevalence of toxic comments on social media platforms has led to varying degrees of harm for individuals. The conventional practice of manually categorizing and blocking such toxic comments has proven to be highly inefficient. To address this issue, this study employs artificial intelligence natural language processing technology to classify social media comments, offering a more effective solution. In the past few years, many algorithms for handling text classification tasks have been introduced and applied in various scenarios. In this work, the author used an LSTM model that can effectively handle long sequence dependency problems to implement text classification. This study achieved an accuracy of 99.4% after training on the Kaggle toxic comments datasets. During the training process, the training accuracy is greater than the validation accuracy while the validation loss is lower than the training loss. After training, the trained model can accurately predict an input sentence and the results are within the expected range.

Patient Experience of Sjögren's Disease and its Multifaceted Impact on Patients' Lives.

The symptoms associated with Sjögren's disease (Sjögren's) are well-documented from the physician's perspective. However, from the patient's perspective, there is limited information on symptoms and their impact on health-related quality of life (HRQoL). This study aimed to provide an expanded understanding of patients' experience of Sjögren's and how symptoms impact HRQoL using a novel multi-method social media listening (SML) approach. A total of 26,950 social media posts with relevant content on Sjögren's posted by social media users from the USA, Canada, Australia, UK, France, Germany, Italy, Spain and China were analysed using an artificial intelligence natural language processing tool to explore patient conversations. Symptoms by level of impact on patients were characterised based on 'commonness' and 'bothersomeness'. Applied concept association analysis was used to assess relationships between symptom domains and impact domains. A qualitative framework was applied to explore words and phrases patients use to describe symptoms and their impacts. Five of the identified symptom domains were very impactful: Pain; Dry Mouth and Throat; Fatigue, Energy and Sleep; Emotional Balance; and Dry Eye. The symptom domains Pain and Dry Mouth and Throat were the most common, while those of Emotional Balance and Fatigue, Energy and Sleep were the most bothersome. Symptom domains most closely associated with four HRQoL impact domains were Fatigue, Energy and Sleep, Dry Mouth and Throat and Dry Eye with Daily Functioning; Fatigue, Energy and Sleep with Financial Health; Emotional Balance with Psychological Wellbeing and Gynaecological Issues with Social Wellbeing. The results of this SML study show that Sjögren's affects diverse aspects of patients' lives, with symptoms extending beyond dry eyes and mouth and impacting daily living and functioning. Because symptoms may affect patients differently, these results highlight the importance of measuring impact on HRQoL to assess patient outcomes and treatment options in routine clinical practice and clinical trials.

Preventing Delayed and Missed Care by Applying Artificial Intelligence to Trigger Radiology Imaging Follow-up

Summary Medical diagnostic imaging studies frequently detect findings that require further evaluation. An initiative at Northwestern Medicine was designed to prevent delays and improve outcomes by engineering reliable follow-up of radiographic findings. An artificial intelligence natural language processing (NLP) system was developed to identify radiology reports containing lung- and adrenal-related findings requiring follow-up. Over 13 months, more than 570,000 imaging studies were screened, of which more than 29,000 were flagged as containing lung-related follow-up recommendations, representing a 5.1% rate of lung-related findings occurrence on relevant imaging studies and an average of 70 findings flagged per day. Northwestern’s prospective clinical validation of the system, the first of its kind, demonstrated a sensitivity of 77.1%, specificity of 99.5%, and positive predictive value of 90.3% for lung findings requiring follow-up. To date, the workflow has generated nearly 5,000 interactions with ordering physicians and has tracked more than 2,400 follow-ups to completion. The authors conclude that NLP demonstrates significant potential to improve reliable follow-up to imaging findings and, thus, to reduce preventable morbidity in lung pathology and other high-risk and problem-prone areas of medicine.

Research on the Application of Artificial Intelligence Natural Language Processing Technology in Japanese Teaching

In the context of artificial intelligence, natural language processing technology has matured and it is a key technology for foreign language teaching and research direction. The application of artificial intelligence natural language processing technology to Japanese teaching is essentially a language processing technology that combines computer science and artificial intelligence. Based on this, this article will analyze the application of artificial intelligence natural language processing technology in Japanese teaching, hoping to have a certain reference significance for Japanese teachers’ educational technology research.

Intelligent compilation of patent summaries using machine learning and natural language processing techniques

Patents are a type of intellectual property with ownership and monopolistic rights that are publicly accessible published documents, often with illustrations, registered by governments and international organizations. The registration allows people familiar with the domain to understand how to re-create the new and useful invention but restricts the manufacturing unless the owner licenses or enters into a legal agreement to sell ownership of the patent. Patents reward the costly research and development efforts of inventors while spreading new knowledge and accelerating innovation. This research uses artificial intelligence natural language processing, deep learning techniques and machine learning algorithms to extract the essential knowledge of patent documents within a given domain as a means to evaluate their worth and technical advantage. Manual patent abstraction is a time consuming, labor intensive, and subjective process which becomes cost and outcome ineffective as the size of the patent knowledge domain increases. This research develops an intelligent patent summarization methodology using artificial intelligence machine learning approaches to allow patent domains of extremely large sizes to be effectively and objectively summarized, especially for cases where the cost and time requirements of manual summarization is infeasible. The system learns to automatically summarize patent documents with natural language texts for any given technical domain. The machine learning solution identifies technical key terminologies (words, phrases, and sentences) in the context of the semantic relationships among training patents and corresponding summaries as the core of the summarization system. To ensure the high performance of the proposed methodology, ROUGE metrics are used to evaluate precision, recall, accuracy, and consistency of knowledge generated by the summarization system. The Smart machinery technologies domain, under the sub-domains of control intelligence, sensor intelligence and intelligent decision-making provide the case studies for the patent summarization system training. The cases use 1708 training pairs of patents and summaries while testing uses 30 randomly selected patents. The case implementation and verification have shown the summary reports achieve 90% and 84% average precision and recall ratios respectively.