Natural Language Processing Analysis Research Articles

Exploring Cognitive Sustainability Concerns in Public Responses to Extreme Weather Events: An NLP Analysis of Twitter Data

The United States has a long history of experiencing extreme weather events. Hurricanes are among the most devastating natural disasters that have significant economic and physical impacts on the country. By applying Natural Language Processing (NLP) to Twitter data for sentiment analysis, emotion detection, and topic modelling, this study provides a more thorough understanding of public response and concerns during five study cases of hurricanes that hit the United States: Harvey, Irma, Maria, Ida, and Ian. The findings on sentiment analysis revealed that 64.75% of the tweets were classified as Negative and 35.25% as Positive. For emotion detection, the predominant emotion was anger, with 39.91%. These results were centred around the main public concerns shown by the topic modelling: hurricane management, donation and support, and disaster impacts. Our future work will focus on understanding people’s responses to extreme weather events through the evolving concept of Cognitive Sustainability.

Psychological Emotion Recognition Of Students Based Chatbot

In the context of modern education, where students' emotional well-being plays a crucial role in academic success, the integration of technology, particularly machine learning-based chatbots, presents a promising avenue to support and recognize the psychological states of students. This paper delves into the development and evaluation of a chatbot system designed to recognize and respond to the emotions expressed by students. Leveraging natural language processing and sentiment analysis, the chatbot engages in conversations with students, allowing for the real-time recognition of emotional states. Our study not only focuses on the technical aspects of emotion recognition but also explores the implications and ethical considerations of deploying such technology in educational settings. By shedding light on the potential of machine learning-based chatbots to enhance emotional support and understanding within educational environments, this research contributes to the ongoing dialogue on student well-being and the role of technology in education.

Towards a typological framework for circular economy roadmaps: A comprehensive analysis of global adoption strategies

This study introduces a novel typological framework for categorising Circular Economy Roadmaps (CERMs) across multiple governance levels, such as national, regional, and sectoral, responding to the fragmented landscape in current literature. Through a comprehensive review and analysis of 398 CE documents, combined with methodological approaches like natural language processing (NLP), topic modelling, and quantitative content analysis, patterns, prevalence, and priority areas in CERMs are expounded. Results underline the pivotal role of governance in CE transitions and spotlight environmental issues, especially sustainable waste management, as dominant motivations. Notably, there appears to be limited private sector involvement in CERM development. Given the inherent regional and sectoral nuances, the findings critically highlight the need for tailored CERM types to facilitate effective transitions.

Teen-adult interactions during the co-design of data literacy activities for the public library: insights from a natural language processing analysis of linguistic patterns

PurposeThe purpose of this study is to explore teen-adult dialogic interactions during the co-design of data literacy activities in order to determine the nature of teen thinking, their emotions, level of engagement, and the power of relationships between teens and adults in the context of data literacy. This study conceives of co-design as a learning space for data literacy. It investigates the teen–adult dialogic interactions and what these interactions say about the nature of teen thinking, their emotions, level of engagement and the power relationships between teens and adults.Design/methodology/approachThe study conceives of co-design as a learning space for teens. Linguistic Inquiry and Word Count (LIWC-22), a natural language processing (NLP) software tool, was used to examine the linguistic measures of Analytic Thinking, Clout, Authenticity, and Emotional Tone using transcriptions of recorded Data Labs with teens and adults. Linguistic Inquiry and Word Count (LIWC-22), a natural language processing (NLP) software tool, was used to examine the linguistic measures of Analytic Thinking, Clout, Authenticity and Emotional Tone using transcriptions of recorded Data Labs with teens and adults.FindingsLIWC-22 scores on the linguistic measures Analytic Thinking, Clout, Authenticity and Emotional Tone indicate that teens had a high level of friendly engagement, a relatively low sense of power compared with the adult co-designers, medium levels of spontaneity and honesty and the prevalence of positive emotions during the co-design sessions.Practical implicationsThis study provides a concrete example of how to apply NLP in the context of data literacy in the public library, mapping the LIWC-22 findings to STEM-focused informal learning. It adds to the understanding of assessment/measurement tools and methods for designing data literacy education, stimulating further research and discussion on the ways to empower youth to engage more actively in informal learning about data.Originality/valueThis study applies a novel approach for exploring teen engagement within a co-design project tasked with the creation of youth-oriented data literacy activities.

Detecting covert disruptive behavior in online interaction by analyzing conversational features and norm violations

Disruptive behavior is a prevalent threat to constructive online engagement. Covert behaviors, like trolling, are especially challenging to detect automatically, because they utilize deceptive strategies to manipulate conversation. We illustrate a novel approach to their detection: analyzing conversational structures instead of focusing only on messages in isolation. Building on conversation analysis, we demonstrate that 1) conversational actions and their norms provide concepts for a deeper understanding of covert disruption, and that 2) machine learning, natural language processing and structural analysis of conversation can complement message-level features to create models that surpass earlier approaches to trolling detection. Our models, developed for detecting overt (aggression) as well as covert (trolling) behaviors using prior studies’ message-level features and new conversational action features, achieved high accuracies (0.90 and 0.92, respectively). The findings offer a theoretically grounded approach to computationally analyzing social media interaction, and novel methods for effectively detecting covert disruptive conversations online.

MSR10 Incidence, Prevalence, and Clinical Characteristics of Patients with Chronic Lymphocytic Leukemia (CLL) in Spain: Natural Language Processing (NLP) Analysis of Electronic Health Records (EHRs)

MSR10 Incidence, Prevalence, and Clinical Characteristics of Patients with Chronic Lymphocytic Leukemia (CLL) in Spain: Natural Language Processing (NLP) Analysis of Electronic Health Records (EHRs)

Twitter Sentiment Analysis on Chatgpt Tweets

Abstract: This study investigates multilingual sentiment analysis within tweets on ChatGPT, an AI conversational model, employing Support Vector Machines (SVM) and BERT, an advanced language model. It aims to detect and classify emotions, including emoji identification, embedded within diverse messages across multiple languages on Twitter. By leveraging SVM's text classification and BERT's contextual understanding in various languages, the research delves into preprocessing techniques and feature engineering for sentiment analysis, encompassing multilingual and emoji detection. Furthermore, it explores the fusion of traditional SVM methods with BERT's state-of-the-art model for multilingual sentiment analysis, emphasizing emotion and emoji detection in AI-generated content on multilingual social media platforms like Twitter. This research yields insights into the successful detection of multilingual sentiment nuances and emotions, including emoji identification. It offers implications for advancing multilingual sentiment analysis in natural language processing across diverse linguistic contexts.

Could Artificial Intelligence be a Therapeutic for Mental Issues?

The utilization of artificial intelligence (AI) possesses the capacity to fundamentally transform the landscape of mental health care through the provision of very valuable therapeutic interventions. AI possesses the capacity to evaluate extensive quantities of data, enabling it to aid in the identification of early signs of mental health concerns and provide tailored solutions that cater to specific requirements. The utilization of virtual therapists powered by AI has the potential to provide a secure environment for persons experiencing social anxiety or worries associated with stigma. This form of therapy offers continuous support and diminishes the obstacles that hinder individuals from seeking assistance. In addition, AI algorithms possess the capability to effectively identify and analyze patterns and trends derived from many sources, including social media posts and smartphone usage. This enables the assessment of an individual’s mental health and facilitates the provision of timely solutions. Through the utilization of natural language processing and sentiment analysis, AI has the potential to augment current therapeutic practices by proficiently monitoring patient advancements and analyzing therapeutic dialogues. Therefore, the incorporation of AI into the realm of mental health intervention holds promise in enhancing accessibility, cost, and efficacy, while mitigating the strain on conventional healthcare systems.

Research on Symptomatic Treatment Decision Support System Based on Natural Language Process (NLP) for Medication Guidance.

This study is to test the technologies related to natural language processing (NLP) and text analysis to solve the problem of symptom analysis and symptomatic treatment for healthcare workers and patients after large-scale outbreaks of infectious diseases. Using the keyword extraction tool based on NLP technology combined with text analysis, the symptom description of the infected population obtained from the questionnaire survey was analyzed, and the efficacy of the symptomatic treatment drug was analyzed, and finally a pre-experimental system of online symptomatic treatment support drug selection system was produced. Through natural language processing (NLP) and text analysis of the symptoms of infected people, we found that high-frequency symptoms were mainly reflected in: nasal congestion, sore throat, fever and other high-frequency keywords, and through the analysis of alternative drug libraries, we also found that the drugs were mainly concentrated in: cold medicines, antipyretic drugs,and traditional Chinese medicines. In the early stage of infectious disease outbreak, it is difficult to use the existing drug library to make a prompt system under the premise of insufficient data collection, and a relatively complete symptomatic treatment support medication system can be formed after accumulating certain samples.

News Classification and Categorization with Smart Function Sentiment Analysis

Search engines are tools used to find information on the Internet. Since the web has a plethora of websites, the engine queries the majority of active sites and builds a database organized according to keywords utilized in the search. Because of this, when a user types a few descriptive words on the home page of the search engine, the search function lists websites corresponding to these keywords. However, there are some problems with this search approach. For instance, if a user wants information about the word Jaguar, most search results are animals and cars. This is a polysemic problem that forces search engines to always provide the most popular but not the most relevant results. This article presents a study of using sentiment technology to help news classification and categorization and improve the classification accuracy. We have introduced a smart search function embedded into a search engine to tackle polysemic issues and record relevant results to determine their sentimentality. Therefore, this study presents a topic that involves several aspects of natural language processing (NLP) and sentiment analysis for news categorization and classification. A web crawler was used to collect British Broadcasting Corporation (BBC) news across the Internet, carried out preprocessing of text by using NLP, and applied sentiment analysis methods to determine the polarity of the processed text data. The sentimentality represents negative, positive, or neutral polarities assigned by the sentiment analysis algorithms. The research utilized the BBC news site to collect different information using a web crawler and a database to explore the sentimentality of BBC news. The natural language toolkit (NLTK) and BM25 indexed and preprocessed patterns in the database. The experimental results depict the proposed search function surpassing normal search with an accuracy rate of 85%. Moreover, the results show a negative polarity of BBC news using the Sentistrength algorithm. Furthermore, the Valence Aware Dictionary and sEntiment Reasoner (VADER) was the best-performing sentiment analysis model for news classification. This model obtained an accuracy of 85% using data collected with the proposed smart function.

An improved Bulgarian natural language processing pipeline

In this paper, we present a language pipeline for processing Bulgarian language data. The pipeline consists of the following steps: tokenization, sentence splitting, part-of-speech tagging, dependency parsing, named entity recognition, lemmatization, and word sense disambiguation. The first two components are based on rules and lists of words specific to the Bulgarian language, while the rest of the components use machine learning algorithms trained on universal dependency data and pretrained word vectors. The pipeline is implemented in the Python library spaCy (https://spacy.io/) and achieves significant results on all the included subtasks. The pipeline is open source and is available on Github (https://github.com/melaniab/spacy-pipeline-bg/) for use by researchers and developers for a variety of natural language processing and text analysis tasks.

Geospatial vaccine misinformation risk on social media: Online insights from an English/Spanish natural language processing (NLP) analysis of vaccine-related tweets

BackgroundMisinformation is known to affect norms, attitudes, and intentions to engage with healthy behaviors. Evidence strongly supports that Spanish speakers may be particularly affected by misinformation and its outcomes, yet current insights into the scope and scale of misinformation is primarily ethnocentric, with greater emphasis on English-language design. ObjectiveThis study applies Natural Language Processing (NLP) to analyze a corpus of English/Spanish tweets about vaccines, broadly defined, for misinformation indicators. MethodsWe analyzed NEnglish = 247,140 and NSpanish = 104,445 tweets using Latent Dirichlet Allocation (LDA) topic models with Coherence score calculation (model fit) with a Mallet adjustment (topic optimization). We used informal coding to name computer-identified topics and compare misinformation scope and scale between languages. ResultsThe LDA analysis yielded a 12-topic solution for English and a 14-topic solution for Spanish. Both corpora contained overlapping misinformation, including uncertainty of research guiding policy recommendations or standing in support of antivax movements. However, the Spanish data were positioned in a global context, where misinformation was directed at government equity and disparate vaccine distribution. ConclusionOur findings support that misinformation is a global issue. However, misinformation may vary depending on culture and language. As such, tailored strategies to combat misinformation in digital planes are strongly encouraged.

Named entity recognition of rice genes and phenotypes based on BiGRU neural networks

Named Entity Recognition (NER) is a fundamental but crucial task in natural language processing (NLP) and big data analysis, with wide application range. NER for rice genes and phenotypes is a technique to identify genes and phenotypes from a large amount of text. NER for rice genes and phenotypes can facilitate the acquisition of information in the field of crops and provide references for our research on higher quality crops. At the same time, named entity recognition still faces many challenges. In this paper, we propose an improved bidirectional gated recurrent unit neural network (BI-GRU) method, which is used to automatically identify the required entities (i.e. gene names, rice phenotypes) from relevant rice literature and patents. The neural network model is combined with the Softmax function to directly output the probabilities of labels, forming the BI-GRU-SF model. With the ability of deep learning methods, the semantic information in the context can be learned without the need for feature engineering. Finally, we conducted experiments, and the results showed that our proposed model provided better performance compared to other models. All datasets and resource codes of BI-GRU-SF are available at https://github.com/qqeeqq/NER for academic use.

Comparison of web-based information about cell-free DNA prenatal screening: implications for differences of sex development care

ObjectiveCell-free DNA (cfDNA) prenatal screening is a commercially available noninvasive test that detects fetal genetic material in maternal blood. While expectant parents often use it for “gender” determination, there is little information about unintended consequences of testing, such as revelation of a difference of sex development (DSD). The study aimed to characterize currently available website information about cfDNA and compare the cfDNA-related content.MethodsA systematic search for websites with information about cfDNA was conducted using search terms generated by a natural language processing analysis of the results of an Amazon Mechanical Turk (MTurk) survey of 1,000 parents and then performing a “Google” search, using the terms. Commercial cfDNA testing companies (CC) websites were also identified by consulting a genetic counselor (AGW). Data were collected on about each website’s characteristics and information about cfDNA. Information about cfDNA was compared between websites. Data were analyzed using descriptive statistics, Fisher’s exact test or Kruskal-Wallis test were applied, as appropriate.ResultsSixty websites were identified. After eliminating duplicates, 11 commercial company (CC) websites were identified. Nineteen other websites were reviewed of which six overlapped with five CC websites. Most of the websites had non-professional authors (73.7%), such as laypersons and CC representatives. CC websites were significantly more likely than search term-identified websites to state that cfDNA can screen for trisomy 21 (p=0.002), trisomy 18 (p<0.0001), trisomy 13 (p<0.001), sex chromosome aneuploidies (p<0.001), and microdeletions (p=0.002).ConclusionsThis study shows that most website currently available information for expectant parents about cfDNA prenatal screening is produced by non-professional organizations. There are significant differences between the information provided by CC and Google search websites, specifically about the number of conditions screened for by cfDNA. Improving availability and quality of information about cfDNA could improve counseling future expectant parents. Inclusion of information about the potential for detection of a DSD is needed.

Revisiting basal cell carcinoma clinical margins: Leveraging natural language processing and multivariate analysis with updated Royal College of Pathologists histological reporting standards

Data supporting the current British Association of Dermatologists guidelines for the management of basal cell carcinoma (BCC) are based on historic studies and do not consider the updated Royal College of Pathologists (RCPath) histological reporting standards. The aim of this study was to use natural language processing (NLP)-derived data and undertake a multivariate analysis with updated RCPath standards, providing a contemporary update on the excision margins required to achieve histological clearance in BCC. A validated NLP information extraction model was used to perform a rapid multi-centre, pan-specialty, consecutive retrospective analysis of BCCs, managed with surgical excision using a pre-determined clinical margin, over a 17-year period (2004-2021) at Swansea Bay University Health Board. Logistic regression assessed the relationship between the peripheral and deep margins and histological clearance. We ran our NLP algorithm on 34,955 BCCs. Out of the 1447 BCCs that met the inclusion criteria, the peripheral margin clearance was not influenced by the BCC risk level (p=0.670). A clinical peripheral margin of 6mm achieved a 95% histological clearance rate (95% confidence interval [CI], 0.93-0.98). Tumour thickness inversely affected deep-margin histological clearance (OR 0.720, 95% CI, 0.525-0.991, p<0.05). Depth level 2 had a 97% probability of achieving deep-margin histological clearance across all tumour thicknesses. Updated RCPath reporting standards minimally impact the peripheral margin histological clearance in BCC. Larger clinical peripheral margins than those indicated by current guidelines may be necessary to achieve excision rates of ≥95%. These findings emphasise the need for continuous reassessment of clinical standards to enhance patient care.

How COVID-19 affects user interaction with online streaming service providers on twitter

The worldwide diffusion of COVID-19, declared pandemic in March 2020, has led to significant changes in people’s lifestyles and behavior, especially when it comes to the consumption of media and entertainment. Indeed, during this period, online streaming platforms have become the preferred providers of recreational content, whereas Online Social Networks proved to be the favorite place to find social connections while adhering to distancing measures. In the meantime, from the online Streaming Service Providers’ point of view, Online Social Networks have gained more and more importance both as valuable data sources for business intelligence and as connected and co-viewing platforms. This study starts from these considerations to explore the impact of COVID-19 on user interaction with Streaming Service Providers in Online Social Networks. In particular, our investigation focuses on the Twitter platform; by comparing several large datasets referring to different periods (i.e., before, during, and after COVID-19 emergence), we investigate interesting patterns and dynamics leveraging both Natural Language Processing and sentiment analysis techniques. Our data science campaign, and the main findings derived, adopts a peculiar perspective focusing on the different categories of users and Streaming Service Providers. The main objective of the analysis is to uncover the dynamics underlying the evolution of the interaction between people and businesses during the COVID-19 outbreak.

Examining the relationship between COVID-19 and suicide in media coverage through Natural Language Processing analysis

Background and objectivesSuicide is a major public health concern, media can influence its awareness, contagion, and prevention. In this study, we evaluated the relationship between the COVID-19 pandemic and suicide in media coverage through Natural Language Processing analysis (NPL). MethodsTo study how suicide is depicted in news media, Artificial Intelligence and Big Data techniques were used to analyze news and tweets, to extract or classify the topic to which they belonged. ResultsA granger causality analysis showed with significant p-value that an increase in covid news at the beginning of the pandemic explains a later rise in suicide-related news. An analysis based on correlation and structural causal models show a strong relationship between the appearance of subjects “health” and “covid”, and also between “covid” and “suicide”. ConclusionsOur analysis also uncovers that the inclusion of suicide-related news in the category health has grown since the outbreak of the pandemic. The COVID-19 pandemic has posed an inflection point in the way suicide-related news are reported. Our study found that the increased media attention on suicide during the COVID-19 pandemic may indicate rising social awareness of suicide and mental health, which could lead to the development of new prevention tools.

Natural language processing analysis of the psychosocial stressors of mental health disorders during the pandemic

Over the past few years, the COVID-19 pandemic has exerted various impacts on the world, notably concerning mental health. Nevertheless, the precise influence of psychosocial stressors on this mental health crisis remains largely unexplored. In this study, we employ natural language processing to examine chat text from a mental health helpline. The data was obtained from a chat helpline called Safe Hour from the “It Gets Better” project in Chile. This dataset encompass 10,986 conversations between trained professional volunteers from the foundation and platform users from 2018 to 2020. Our analysis shows a significant increase in conversations covering issues of self-image and interpersonal relations, as well as a decrease in performance themes. Also, we observe that conversations involving themes like self-image and emotional crisis played a role in explaining both suicidal behavior and depressive symptoms. However, anxious symptoms can only be explained by emotional crisis themes. These findings shed light on the intricate connections between psychosocial stressors and various mental health aspects in the context of the COVID-19 pandemic.

Developing a Word Lexicon from Electronic Health Records for Natural Language Processing Analysis of Free-Text Reports for Patients with Venous Thromboembolism.

Patients with gliomas, particularly glioblastomas (GBM) have a higher risk of developing venous thromboembolism (VTE), including both pulmonary embolism (PE) or deep vein thrombosis (DVT), both correlating with overall survival (OS) and potential biological signaling relevance for analysis of the tumor state in conjunction with evolving biomarkers. Artificial intelligence (AI) approaches thar employ VTE as a clinical feature in brain tumor patients is understudied due to the difficulty in analyzing unstructured clinical data in electronic health records (EHR). Data expansion by creating a word lexicon for natural language processing (NLP) of free-text clinical reports will allow exposure of VTE for classification of large-scale data sets, NLP and AI. Patients with a pathologic diagnosis of GBM (2005-2021) were extracted from EHR and screened for the development of VTE based on radiology free-text reports - ultrasound (US) of extremities and Computed Topography-pulmonary angiogram (CT). Language data were collected manually and verified computationally using radiology report text filtration. Common phrases and words employed were collected to generate a lexicon for future computational analysis. Kaplan-Meier survival analyses were generated for VTE in relation OS and progression-free survival (PFS). A total of 163 patients (mean age = 56.1 ± 12.1, 65% male) were included, 48 (29.4%) were screened for VTE following clinical suspicion on history or physical exam, and 15 (9.2%) were found to have a VTE. Screening methods were US 83.3% (40) or CT 13.9% (6), or both 4.6% (2). 28.6% (12) of US and 37.5% (3) of CT resulted in a positive VTE diagnosis. Terms that were only detected in patients with VTE were for US: "complete" 44%, "thrombosis detected" (8.3%), "occlusive" (16%), "partial" (16%), "critical" (25%), "residual" (8.3%) and for CT: "critical" (67%) and "pulmonary emboli" (33%). Words used in free-text reports showed a high degree of inter-reporter variability. The words "partial", "residual", "complete", "critical" or "clotted" when used as an "or" Boolean statement applied to US and CT radiology reports identified ∼93% of the patients with VTE. Patients with VTE had worse OS (median 14 vs. 19 months, p = .0189) and PFS (median 6 vs. 9 months, p = .0239) compared to patients without VTE indicating underlying pathology associated with both prevalence of VTE and tumor burden and the need to incorporate VTE as a clinical feature in large scale data analyses. US and CT yield a similar percentage of positive VTE findings while employing different terms to characterize VTE. We confirm that patients with VTE have poorer outcomes and present a word combination that identifies patients with VTE in large-scale radiology report data. Further research will focus on validation in other datasets, NLP approaches to optimize and data aggregation with laboratory data and large-scale omics panels to expose thrombosis as a clinical feature for biomarker analysis.

Measuring flight-destination similarity: A multidimensional approach

E-tourism websites offer users a vast array of travel destinations and opportunities, necessitating tools that enable destination comparison and intelligent search capabilities. One key requirement for such tools is the ability to measure the similarity between destinations. Over the years, various similarity measurement techniques have been proposed, including user-based and content-based approaches. However, many of these techniques require data preparation or prior domain knowledge from experts. In contrast, this study proposes an innovative approach that requires no prior domain knowledge of flight destinations or their relationships, and utilizes only readily available data. Our approach draws upon concepts from image recognition and natural language processing (NLP) to extract hidden aspects of destinations. Using data from a flight-search website as a testbed, we analyze similarity metrics based on state-of-the-art methods for image recognition, NLP, and product-network analysis. We then compare these metrics to those obtained by human subjects. Our findings suggest that no single method dominates in all aspects, leading us to propose a hybrid method that leverages the strengths of each. The proposed method can be readily applied to measure product similarity in other domains.