List Of Keywords Research Articles

Transparency of social-economic determinants in developing the efficient public healthcare system

In the modern society, public healthcare and safe life are key tasks of any country worldwide. Social health and security are the highest and the most desired values. They are integral conditions to reach sustainable development goals. Healthcare is an important policy component of separate states and supernational communities worldwide. The issue of global approaches to healthcare and environment protection is one of the most outstanding scientific achievements of the 20th century. The current article reviews arguments in researching the public healthcare system. The main study purpose is a detailed analysis of the social-economic public healthcare determinants and their transparency in the 2013-2023 Scopus sources. The research object is public healthcare. The research topic is bibliometric analysis of the 2013-2023 Scopus sources about public healthcare. The bibliometric analysis of big data provides us with those necessary research results that cannot be obtained without special tools. To conduct the public healthcare bibliometric analysis, we applied the VOSviewer computer software. It engages wide functional possibilities of smart text processing, which generates and visualises joint networks of the most significant terms and notions in a certain branch. A thorough bibliometric analysis of the social-economic public healthcare determinants and their transparency in the 2013-2023 Scopus sources is conducted stepwise. Firstly, we select a list of keywords for the studied issue. Secondly, the Scopus search engine is activated. Thirdly, a range of sources is defined. Fourthly, we analyse a sample of Scopus publications. Fifthly, we conduct the VOSviewer cluster analysis of the Scopus sources (arranged by citation number, co-authorship frequency, countries with the given problem). Sixthly, we examine bibliometric maps with visualised clusters. The obtained research results may definitely contribute to further healthcare studies and bibliometric analysis of indexed scientific sources.

Who Tells Your Story? Analyzing a Century of Utah History

Who Tells Your Story? Analyzing a Century of Utah History

Documenting the Rise of Anxiety in the United States across Space and Time by Using Text Analysis of Online Review Data

In this article, the author demonstrates how one can use large-scale and publicly available online review data to study the rise in anxiety in the United States. Using the anxiety keyword list from the dictionary compiled by Linguistic Inquiry and Word Count, the author analyzed the text of approximately 7 million online reviews submitted by Yelp reviewers across 13 U.S. states from 2006 to 2021. The overall pattern confirms existing discourse that anxiety has been constantly rising in Western societies since 2000. Beyond documenting the overall pattern, online review data enable the disaggregation of this pattern by geographies, price levels, and individuals, thereby providing a more comprehensive and detailed picture than previously documented in existing literature. Additional analysis shows that anxiety is increasing faster than other emotions, such as anger and sadness.

A Corpus-based Approach to Frame ‘COVID-19 Vaccination’ in Malaysian English Newspapers

Most studies on COVID-19 have been massively dedicated on how the disease was framed in the newspaper, its psychological effects, and its message or content disinformation. Research on the COVID-19 vaccination in newspapers and its acceptance among the masses is still quite scarce. The study adopted a corpus approach that involves wordlist, keyword list, collocates, and concordance analysis to analyse how ‘COVID-19 vaccination’ was framed in a focused and specialised English Malaysian newspapers corpus. #Lanscbox 5.0 corpus tool was employed in conducting the empirical analysis. The empirical analysis revealed that ‘COVID-19 vaccination’ was positively framed in different ways in the newspaper. The analysis of collocates and concordance lines revealed that the news reports mainly used Solution-oriented Frame which highlighted the Malaysian government’s effort in combating the pandemic. The newspaper was also found to use Mathematical frame in the effort to convince the public with regards to the updates and statistics of vaccine takers. Nevertheless, the results also revealed the usage of sensational phrases that framed the COVID-19 vaccination negatively. These findings can enlighten newspaper practitioners on what should be done and avoided in framing such an issue in their writings as well as how the public will perceive it. Keywords: Corpus-based analysis, COVID-19, mass media, news article, vaccination.

Factors that Influence Followers to Be a Future Ethical Leader

This literature review study connects such elements to relevant ethical theories (such as utilitarianism, libertarianism, Kant's ethical theory, and fairness and justice), focusing on the characteristics that empower people to become future ethical leaders. This research attempts to investigate the idea of ethical leadership, the significance of ethical leadership in an organization, determining components to be an ethical leader, and strategies to turn followers into ethical leaders from the intersection of the literature reviews on ethics and leadership. A major research question directed the study: what are the factors that inspire followers to become future ethical leaders? Based on data found from the various books and articles, different databases and a list of keywords used during the search. According to the research outcomes, two key influences—(a) an individual's moral worldview and (b) organizational culture and ethics—can motivate followers to become moral leaders. Family influences, religious conviction, educational institutions, peer influences, and culture have an impact on an individual's moral philosophy. Besides organizational culture and ethics consists of code of conduct, work-life balance, recruitment procedure, compensation plan, role model, training, and further development. The influencing factors were discussed and recommended further research area. The relevant elements were explored, and further research area was suggested. IUBAT Review—A Multidisciplinary Academic Journal, 5 (1): 77-88

Guide for authors: jCEC Template 2023

This document gives formatting instructions for authors preparing articles for publication in the jCEC journal. The authors must follow the instructions given in the document for the articles to be published. You can use this document as both an instruction set and as a template into which you can type your own text. Abstract should be no longer than 1000 characters including spaces (or from 200 to 300 words). It gives a brief summary of the content of the main objective, the methods, the results obtained and major conclusions. Translation of the abstract to an appropriate language must be provided here. Please choose either Portuguese or Spanish, and adapt your list of keywords accordingly.

Методичні засади контент-аналізу сайтів

Abstract. Introduction. It has been established that content analysis is a method of quantitative and qualitative study of content to measure or identify certain trends and facts reflected in the texts proposed for study. The first examples of content analysis began to appear in social disciplines starting from the 30s of the last century in the USA. The basic system of content analysis includes: quick update of content, search for content on a certain resource, collection of content about regular and potential customers, audience analysis, analysis of resource visits. It is necessary to analyze the content of the site when the main tasks of the virtual project are not solved quickly enough or too efficiently. Quantitative content analysis is characterized by the frequency of occurrence of certain characteristics in the text. Qualitative content analysis - involves studying the form and structure of content. Nine stages of content analysis are distinguished: analysis of the situation, drawing up a plan, drawing up descriptions; site scanning. Analysis of descriptions for all types of products offered on the site; checking the effectiveness of the content - number of views, number of unique visitors, citations, rejection rate; entering information about keywords/phrases. Creating a map of keywords/phrases for the pages that are considered most significant; studying keywords. Analysis of query statistics for a list of keywords; integration of information from keywords. Determination of key phrases, the number of requests, information about the competition, entering information into the table; determining which content is missing.Definition of additional keywords and content corresponding to them; analysis of additional parameters of virtual pages. Research of popular and unpopular pages, pages with an increased level of risk (contain copied materials or information that does not cause any interest), improvement of publications; making recommendations. Selected software tools for site content analysis: Screaming Frog, XML-sitemaps.com, URL Profiler, Google Ads.

A comparison of approaches for imbalanced classification problems in the context of retrieving relevant documents for an analysis.

One of the first steps in many text-based social science studies is to retrieve documents that are relevant for an analysis from large corpora of otherwise irrelevant documents. The conventional approach in social science to address this retrieval task is to apply a set of keywords and to consider those documents to be relevant that contain at least one of the keywords. But the application of incomplete keyword lists has a high risk of drawing biased inferences. More complex and costly methods such as query expansion techniques, topic model-based classification rules, and active as well as passive supervised learning could have the potential to more accurately separate relevant from irrelevant documents and thereby reduce the potential size of bias. Yet, whether applying these more expensive approaches increases retrieval performance compared to keyword lists at all, and if so, by how much, is unclear as a comparison of these approaches is lacking. This study closes this gap by comparing these methods across three retrieval tasks associated with a data set of German tweets (Linder in SSRN, 2017. 10.2139/ssrn.3026393), the Social Bias Inference Corpus (SBIC) (Sap et al. in Social bias frames: reasoning about social and power implications of language. In: Jurafsky et al. (eds) Proceedings of the 58th annual meeting of the association for computational linguistics. Association for Computational Linguistics, p 5477-5490, 2020. 10.18653/v1/2020.aclmain.486), and the Reuters-21578 corpus (Lewis in Reuters-21578 (Distribution 1.0). [Data set], 1997. http://www.daviddlewis.com/resources/testcollections/reuters21578/). Results show that query expansion techniques and topic model-based classification rules in most studied settings tend to decrease rather than increase retrieval performance. Active supervised learning, however, if applied on a not too small set of labeled training instances (e.g.1000 documents), reaches a substantially higher retrieval performance than keyword lists.

740. Does Natural Language Processing Improve Identification of Hospitalized People Who Use Drugs?

Abstract Background In the absence of substance use disorder treatment and harm reduction tools, people who use drugs (PWUD) are at increased risk for severe injection-related infections (SIRI). Health services research characterizing the scope and trends of hospitalizations for SIRI often requires administrative billing records, urine toxicology, and medications to treat opioid use disorder, often supplemented with manual chart review. The goal of this research was to examine the feasibility of using natural language processing (NLP) to augment traditional systems of PWUD. We explored the practicality of using Natural Language Processing as a tool to accurately identify PWUD in electronic medical records (EMR). Methods We worked with information technology/computer science specialists to create a cohort of all people hospitalized at Tufts Medical Center from January 1, 2020, to April 1, 2022. Patients entered this cohort through the presence of any of these criteria: ICD10 codes for substance use disorder, positive urine toxicology results for drugs (including opiates, cocaine, amphetamine), prescriptions for medications to treat substance use disorder (at admission, during hospitalization or discharge) and the presence of NLP keywords. The NLP keyword list was created through iterative meetings with IT specialists (Table 1). Results There were 3102 patients with 3501 hospitalizations. The Venn Diagram (Figure 1) displays the overlap of the 4 criteria. Only 55 people were identified by NLP terms only. The most frequent criteria filled for cohort entry was the toxicology screen. Only 4.1% of the group had all 4 criteria. Conclusion Identifying PWUD using an NLP algorithm was possible, but there was a small number of people who were added to the cohort only on NLP criteria. Improved methodologies of identifying PWUD with medical needs are necessary to better identify gaps in healthcare, facilitate benchmarking of quality care, and improve the lives of PWUD. Disclosures All Authors: No reported disclosures.

Monitoring and Identifying Emerging e-Cigarette Brands and Flavors on Twitter: Observational Study.

Flavored electronic cigarettes (e-cigarettes) have become very popular in recent years. e-Cigarette users like to share their e-cigarette products and e-cigarette use (vaping) experiences on social media. e-Cigarette marketing and promotions are also prevalent online. This study aims to develop a method to identify new e-cigarette brands and flavors mentioned on Twitter and to monitor e-cigarette brands and flavors mentioned on Twitter from May 2021 to December 2021. We collected 1.9 million tweets related to e-cigarettes between May 3, 2021, and December 31, 2021, by using the Twitter streaming application programming interface. Commercial and noncommercial tweets were characterized based on promotion-related keywords. We developed a depletion method to identify new e-cigarette brands by removing the keywords that already existed in the reference data set (Twitter data related to e-cigarettes from May 3, 2021, to August 31, 2021) or our previously identified brand list from the keywords in the target data set (e-cigarette-related Twitter data from September 1, 2021, to December 31, 2021), followed by a manual Google search to identify new e-cigarette brands. To identify new e-cigarette flavors, we constructed a flavor keyword list based on our previously collected e-cigarette flavor names, which were used to identify potential tweet segments that contain at least one of the e-cigarette flavor keywords. Tweets or tweet segments with flavor keywords but not any known flavor names were marked as potential new flavor candidates, which were further verified by a web-based search. The longitudinal trends in the number of tweets mentioning e-cigarette brands and flavors were examined in both commercial and noncommercial tweets. Through our developed methods, we identified 34 new e-cigarette brands and 97 new e-cigarette flavors from commercial tweets as well as 56 new e-cigarette brands and 164 new e-cigarette flavors from noncommercial tweets. The longitudinal trend of the e-cigarette brands showed that JUUL was the most popular e-cigarette brand mentioned on Twitter; however, there was a decreasing trend in the mention of JUUL over time on Twitter. Menthol flavor was the most popular e-cigarette flavor mentioned in the commercial tweets, whereas mango flavor was the most popular e-cigarette flavor mentioned in the noncommercial tweets during our study period. Our proposed methods can successfully identify new e-cigarette brands and flavors mentioned on Twitter. Twitter data can be used for monitoring the dynamic changes in the popularity of e-cigarette brands and flavors.

Company Performance Analysis in Management: Current Preferences and Possible Trends

The objective of this paper is to identify key expressions appearing in scientific papers related to the management of company performance and its analysis. There are various ways of looking at the evaluation of performance of a company. Most commonly they fit into the following categories: financial, social, environmental, and global. Based on a study of several papers and publications in the field of company performance evaluation a list of key words and expressions was set up. These were then evaluated for number of occurrences in google.com search engine in 5-year intervals from 2000 to 2020 included. Similar measurements were done with the google trends tool where monthly “popularity” is measured by the companies own index since 2004. Results show an increase of popularity in social and environmental performance evaluation. Approaches such as the Triple Bottom Line reporting and the Global reporting initiative gain volume in terms of publications on the internet. They are likely to be complemented by tools/approaches related to sustainability and RMSE and ensemble model methods.

Identifying Profiles and Symptoms of Patients With Long COVID in France: Data Mining Infodemiology Study Based on Social Media.

Long COVID-a condition with persistent symptoms post COVID-19 infection-is the first illness arising from social media. In France, the French hashtag #ApresJ20 described symptoms persisting longer than 20 days after contracting COVID-19. Faced with a lack of recognition from medical and official entities, patients formed communities on social media and described their symptoms as long-lasting, fluctuating, and multisystemic. While many studies on long COVID relied on traditional research methods with lengthy processes, social media offers a foundation for large-scale studies with a fast-flowing outburst of data. We aimed to identify and analyze Long Haulers' main reported symptoms, symptom co-occurrences, topics of discussion, difficulties encountered, and patient profiles. Data were extracted based on a list of pertinent keywords from public sites (eg, Twitter) and health-related forums (eg, Doctissimo). Reported symptoms were identified via the MedDRA dictionary, displayed per the volume of posts mentioning them, and aggregated at the user level. Associations were assessed by computing co-occurrences in users' messages, as pairs of preferred terms. Discussion topics were analyzed using the Biterm Topic Modeling; difficulties and unmet needs were explored manually. To identify patient profiles in relation to their symptoms, each preferred term's total was used to create user-level hierarchal clusters. Between January 1, 2020, and August 10, 2021, overall, 15,364 messages were identified as originating from 6494 patients of long COVID or their caregivers. Our analyses revealed 3 major symptom co-occurrences: asthenia-dyspnea (102/289, 35.3%), asthenia-anxiety (65/289, 22.5%), and asthenia-headaches (50/289, 17.3%). The main reported difficulties were symptom management (150/424, 35.4% of messages), psychological impact (64/424,15.1%), significant pain (51/424, 12.0%), deterioration in general well-being (52/424, 12.3%), and impact on daily and professional life (40/424, 9.4% and 34/424, 8.0% of messages, respectively). We identified 3 profiles of patients in relation to their symptoms: profile A (n=406 patients) reported exclusively an asthenia symptom; profile B (n=129) expressed anxiety (n=129, 100%), asthenia (n=28, 21.7%), dyspnea (n=15, 11.6%), and ageusia (n=3, 2.3%); and profile C (n=141) described dyspnea (n=141, 100%), and asthenia (n=45, 31.9%). Approximately 49.1% of users (79/161) continued expressing symptoms after more than 3 months post infection, and 20.5% (33/161) after 1 year. Long COVID is a lingering condition that affects people worldwide, physically and psychologically. It impacts Long Haulers' quality of life, everyday tasks, and professional activities. Social media played an undeniable role in raising and delivering Long Haulers' voices and can potentially rapidly provide large volumes of valuable patient-reported information. Since long COVID was a self-titled condition by patients themselves via social media, it is imperative to continuously include their perspectives in related research. Our results can help design patient-centric instruments to be further used in clinical practice to better capture meaningful dimensions of long COVID.

Know How to Make the Media Work for You

Having a great relationship with the press is paramount in getting them to pay attention to your organization's events and programs. Building that relationship requires going the extra mile with your local media. Jennifer Hines, chief communications officer for Tyler ISD (Tyler, TX), says building a great relationship with the press simply comes down to making their lives easier. “Provide everything they need up front, and let them know what elements you will have available for the story. Also, when they are on location, help carry their equipment, open the door for them and ask about their family or interests,” she says. “We like to thank them on social media and share their story on our social media channels. We also hand out different stories to the various media outlets so they can be the only ones to have it first.” To help make it easy for the reporters, packets are given that include quick facts about the school district, says Hines. It also has a map with the locations of all Tyler ISD's campuses and facilities, abbreviations commonly used in the education industry, logos for each campus and media guidelines. “Because we are in a TV market where most reporters are fresh out of school, we found this was very helpful for them,” explains Hines. Making the media's lives easier also expands to how you craft your press releases. Hines says you'll get better responses from the media when you give them all the elements they need without leaving the newsroom. “We include all the details and quotes from more than one source,” she says. “We even add extra information at the bottom, including our social media handles, a web description for them to use when posting to the web, a list of keywords and even a social media headline. We also try to include a day and time for media availability with more than one person they can interview. We also will include any pictures, logos and videos.” Hines advises, when writing press releases, keep the length to one page, at most, a page and a half for extra pieces. After sending the press release, she says if you haven't heard from the media, reach out to them directly. “I've managed to get the cellphone numbers of key players so I can text them directly. I also make sure to have a good working relationship with the assignment editors, news directors, assistant news directors, editors and reporters. Every time I am on a story with a new reporter, I am intentional about getting their information and adding it to our media list.” Source: Jennifer Hines, Chief Communications Officer, Tyler ISD, Tyler, TX. Phone (903) 262-1064. Email: Jennifer.Hines@tylerisd.org. Website: tylerisd.org

Management of adverse events related to first-generation tyrosine receptor kinase inhibitors in adults: a narrative review.

The aim of this article is to conduct a literature review on first-generation TRK inhibitors (TRKi), namely entrectinib and larotrectinib, to describe the most common adverse events (AEs) and their management in adults. A search strategy was conducted in MEDLINE, EMBASE, and Google Scholar using a list of predetermined keywords. Peer-reviewed articles written in English and published through June 2021 were included. Articles covered included randomized clinical trials and expert recommendations, as well as patent and other types of reviews. The discussed AEs include weight gain and withdrawal pain, as well as neuromuscular, central nervous system (dysesthesias and peripheral sensory neuropathies, dizziness and ataxia, and dysgeusia), gastrointestinal (nausea, vomiting, and diarrhea), and respiratory symptoms. Additionally, several AEs encountered with entrectinib specifically (cognitive and vision disorders, congestive heart failure, QTc elongation, and skeletal fractures) are discussed. First, an overall mechanism of action explaining these AEs is presented. Then, for each AE, incidence and severity are stated and followed by practical management recommendations. While nearly all AEs were reversible upon TRKi suspension, the proposed managements are mainly constituted of pharmacological and non-pharmacological interventions. With the estimated growth of gene sequencing in the coming years, it is foreseeable that TRKi will take a larger position in the oncologic therapeutic arsenal. Therefore, adequate management of AEs associated with TRKi in adults should be a prime focus.

Association between Air Quality and Children’s Restorative Experience: A Systematic Review

Prior studies conducted within the realm of environmental psychology and public health have shown that air pollution exposure exerts significant effects on both physical and psychological well-being, especially for children. The roles of air pollution exposure are being increasingly recognized as essential factors influencing children’s restoration. This systematic review provides an overview of existing knowledge of the impact of air pollution on children’s mental health and restorative experience in both outdoor and indoor environments. A list of keywords for paper selection was derived from a systematic investigation of the literature on children’s restorative environments. A total of 228 studies were initially identified, 18 of which met the eligibility criteria. This systematic review summarizes distinctive categories of air pollutants and discusses the assessments for both air pollution exposure and children’s restorative outcomes. Additionally, 16 barriers in air pollution exposure to children’s restorative experience were identified. The findings of this systematic review were concluded in an integrated framework, which have important implications for developing evidence-based and cross-disciplinary research on the air quality and children’s restoration.

CREATION OF QUESTIONNAIRE KEYWORDS WITH THE CISE METHOD FOR KMS USER SATISFACTION EVALUATION

This study aims to obtain user satisfaction factors for a knowledge management system so that a questionnaire can be made for evaluation or measurement. The SECI method is used with the CISE sequence which consists of four knowledge creation steps, namely C-combination, I-nternalization, S-socialization, and ending E-externalization. The stage begins with literature studies and then modifications are made with the selection, addition, and incorporation of existing models. From understanding and analyzing several models, discussions or brainstorming with colleagues were then carried out so that a final model was obtained to compile a list of keywords and statements as a questionnaire based on indicators related to knowledge management and the satisfaction of knowledge management system users. The results obtained there are eight user satisfaction factors divided into technical aspects (knowledge quality, knowledge sharing, system quality, service quality) and social aspects (management support, system use, perceived usefulness, user attribute). Five attributes were obtained from each of these factors as keywords resulting in 40 questionnaire statements. It can be concluded that the factors of user satisfaction knowledge management system can be built from the satisfaction of information system users in general by adding distinctive factors including the creation, transfer, and documentation of knowledge.

Vowel categorization accuracy and its relationship to phonemic awareness

Cross-language speech perception studies regularly employ categorization tasks to determine listeners’ repertoire of phonological categories. In these tasks, participants select a phoneme from a list of letters or keywords to indicate which speech category they heard. However, recent studies have shown poor categorization accuracy when native (L1) English speakers are asked to categorize English vowels. Categorization tasks require phonemic awareness (PA), the explicit knowledge that words consist of segments, which is acquired alongside alphabetic literacy. Individual differences in PA may account for variability in L1 categorization accuracy. That is, participants with poor phonemic awareness may have difficulty explicitly identifying phonemes in a categorization task, particularly for English vowels, where grapheme-phoneme correspondences are relatively opaque. To test whether PA is related to categorization accuracy, 115 L1 English listeners completed an L1 vowel categorization task and three PA tasks: phoneme counting, deletion, and reversal. Strong correlations were observed between categorization accuracy and all three PA tasks, suggesting PA may account for a substantial proportion of individual variability in vowel categorization tasks. This finding questions the utility of the categorization task for determining listeners’ phonemic categories and has further implications for assessing second language speech categories.

Psychosocial Needs of Gynecological Cancer Survivors: Mixed Methods Study.

BackgroundInternet and social media platforms offer insights into the lived experiences of survivors of cancer and their caregivers; however, the volume of narrative data available is often cumbersome for thorough analysis. Survivors of gynecological cancer have unique needs, such as those related to a genetic predisposition to future cancers, impact of cancer on sexual health, the advanced stage at which many are diagnosed, and the influx of new therapeutic approaches.ObjectiveThis study aimed to present a unique methodology to leverage large amounts of data from internet-based platforms for mixed methods analysis. We analyzed discussion board posts made by survivors of gynecological cancer on the American Cancer Society website with a particular interest in evaluating the psychosocial aspects of survivorship.MethodsAll posts from the ovarian, uterine, and gynecological cancers (other than ovarian and uterine) discussion boards on the American Cancer Society Cancer Survivors Network were included. Posts were web scraped using Python and organized by psychosocial themes described in the Quality of Cancer Survivorship Care Framework. Keywords related to each theme were generated and verified. Keywords identified posts related to the predetermined psychosocial themes. Quantitative analysis was completed using Python and R Foundation for Statistical Computing packages. Qualitative analysis was completed on a subset of posts as a proof of concept. Themes discovered through latent Dirichlet allocation (LDA), an unsupervised topic modeling technique, were assessed and compared with the predetermined themes of interest.ResultsA total of 125,498 posts made by 6436 survivors of gynecological cancer and caregivers between July 2000 and February 2020 were evaluated. Of the 125,489 posts, 23,458 (18.69%) were related to the psychosocial experience of cancer and were included in the mixed methods psychosocial analysis. Quantitative analysis (23,458 posts) revealed that survivors across all gynecological cancer discussion boards most frequently discussed the role of friends and family in care, as well as fatigue, the effect of cancer on interpersonal relationships, and health insurance status. Words related to psychosocial aspects of survivorship most often used in posts included “family,” “hope,” and “help.” Qualitative analysis (20 of the 23,458 posts) similarly demonstrated that survivors frequently discussed coping strategies, distress and worry, the role of family and caregivers in their cancer care, and the toll of managing financial and insurance concerns. Using LDA, we discovered 8 themes, none of which were directly related to psychosocial aspects of survivorship. Of the 56 keywords identified by LDA, 2 (4%), “sleep” and “work,” were included in the keyword list that we independently devised.ConclusionsWeb-based discussion platforms offer a great opportunity to learn about patient experiences of survivorship. Our novel methodology expedites the quantitative and qualitative analyses of such robust data, which may be used for additional patient populations.

Natural language model for automatic identification of Intimate Partner Violence reports from Twitter.

Intimate partner violence (IPV) is a preventable public health problem that affects millions of people worldwide. Approximately one in four women are estimated to be or have been victims of severe violence at some point in their lives, irrespective of age, ethnicity, and economic status. Victims often report IPV experiences on social media, and automatic detection of such reports via machine learning may enable improved surveillance and targeted distribution of support and/or interventions for those in need. However, no artificial intelligence systems for automatic detection currently exists, and we attempted to address this research gap. We collected posts from Twitter using a list of IPV-related keywords, manually reviewed subsets of retrieved posts, and prepared annotation guidelines to categorize tweets into IPV-report or non-IPV-report. We annotated 6,348 tweets in total, with the inter-annotator agreement (IAA) of 0.86 (Cohen's kappa) among 1,834 double-annotated tweets. The class distribution in the annotated dataset was highly imbalanced, with only 668 posts (~11%) labeled as IPV-report. We then developed an effective natural language processing model to identify IPV-reporting tweets automatically. The developed model achieved classification F1-scores of 0.76 for the IPV-report class and 0.97 for the non-IPV-report class. We conducted post-classification analyses to determine the causes of system errors and to ensure that the system did not exhibit biases in its decision making, particularly with respect to race and gender. Our automatic model can be an essential component for a proactive social media-based intervention and support framework, while also aiding population-level surveillance and large-scale cohort studies.

Sentiment Analysis of China-Related News in The Star Online Newspaper

As China and Malaysia approach their 47th year of diplomatic relationships, cooperation and trust between the two countries have deepened in aspects ranging from politics to economy. Despite this mutual reliance, the relationship between Malaysia and China is not without its conflicts and these conflicts are often manifested in media reports. How China is presented in Malaysia news is a field that has been scarcely explored. As part of the research on media sentiment towards China, this research investigates the general sentiment of China-related news in Malaysian media through sentiment analysis of some selected news coverages. Selecting China-related news in The Star Online from 2012 to 2021 as the data for investigation,the Excel Add-in tool Azure Machine Learning was used to generate polarity of these news reports automatically and corpus tool Wordsmith was used for the analysis of news discourse. A total of 137,475 pieces of news have been collected as the research sample. The finding reveals that: 1) despite the large proportion of news with negative sentiment in China-related news in The Star Online , the monthly trend of sentiment shows a slight increase of positiveness over time; 2) an investigation into the keyword lists of three months with highest proportion of negativeness and collocates of the top keywords, however, shows that negative sentiment of the news may be due to a global conflict at that particular time and does not necessarily indicate negative sentiment towards China. A combination of sentiment analysis and corpus approach on the study of China-related news in Malaysian media enriches the study of news discourse from the perspective of corpus linguistics.