Related Keywords Research Articles

Augmented Reality for Education: A Bibliometric Analysis Using VOSviewer

This review aims to present a comprehensive knowledge mapping and analysis of Augmented Reality in education by conducting bibliometric analysis. This study will provide insight into the scope of research, the most frequently emerging research trends, and other areas in education. The use of AR in education has become an interesting topic for researchers over the past few years, presenting significant progress and transformation in educational technology that can improve students' understanding in the learning process. The data was taken from the Scopus database which discusses the use of Augmented Reality in the field of education and found 1396 journal articles. Based on the results of VOSviewer data processing with the topic of augmented reality in education, 4,2561 keywords were found. and related keywords were limited to 9 keywords. and 103 related keywords were found. Bibliometrics can improve the understanding of augmented reality and provide many contributions by discussing keywords used in the literature and grouping research trends and providing directions for further research.

The Applications of Social Media for Luxury Brand Management — A Narrative Review

Purpose — The emergence of social media and digital technologies has reformed the competitive aspect for firms that quickly acknowledged the increasing relevance of social media platforms for business purposes social media is emerging as an important part of our lives. Luxury brands are gaining popularity as the customers are getting richer. In this paper, we did an extensive review of the research papers to understand the applications of social media for luxury brands management. We also studied the data analysis techniques used in those research papers. Methodology — The papers related to the applications of social media for luxury brand management were collected using related keywords. We searched the papers with the keywords such as “Social media marketing” and “Luxury brands”, “Social media consumer engagement” and “Luxury brands”, “Social media consumer response” and “Luxury brands” and “Social media communication” and “Luxury brands” in Scopus database. Findings — Marketing and customer response are the two main categories of the applications of the social media for luxury brand management. Regarding data analysis techniques, traditional data analysis models such as structural equation modelling, regression, etc. have been used more as compared to data mining, text mining, etc. process. Originality — We propose a new categorisation of different research papers related to applications of social media for luxury brand management. We also did an extensive study of the data analysis techniques to conclude that traditional data analysis models have been mostly used in this research area. The recommendations to social media marketing professionals related to luxury brands have been presented to improve the effectiveness of social media campaigns for luxury brands. We also suggest challenges and future research directions in this area.

Meditation modalities for ADHD in minority pediatric populations in the USA: a scoping review.

Roughly 10% of children aged 3 -17 in the USA are diagnosed with attention-deficit hyperactivity disorder (ADHD), and minorities are less likely to initiate common pharmacologic treatment. We conducted a review of the literature to examine meditation as a safe, effective, and low-cost alternative. We searched PubMed and other journals using "meditation," "mindfulness," "minority," related keywords, and relevant MeSH terms. Eligible studies involved racial/ethnic minorities in the USA, reported quantitative psychosocial outcomes, and were published in a peer-reviewed, English-language journal. Out of 119 "hits," 111 were eliminated as duplicates or were not relevant. A full-text review of the remaining eight revealed that none fully met our eligibility criteria. Besides the obvious lack of studies, those reviewed reported incomplete demographic and clinical data. They also employed different and inconsistent research methodologies, interventions and modalities, and statistical analyses. This hindered understanding exactly which populations may benefit from meditation, and for which specific symptoms. We recommend a socio-ecological model in examining intervention modalities, especially in the context of intrapersonal, interpersonal, organizational, environmental, and policy domains. We also suggest the possible inclusion of research older than 10 years, conducted outside of the USA, on minority and non-minority populations, for supplementary and confirmatory data. We advocate for consistency in study design and data collection, which would help align research conducted in different countries. Searches should also include variations of meditation such as "mindfulness" and "guided imagery," and associated symptoms and comorbidities of ADHD, including "learning disorder" and "behavioral problems."

Possibilities and Limitations of Biodegradable Plastics

This study examined societal interest in biodegradable plastics as portrayed in South Korean media, analyzing trends, topics, and related keywords to understand public perceptions and discourse. Big data analysis was conducted on news articles from 104 major South Korean media outlets between 2014 and 2023 using the BIGKinds platform. The frequency of articles mentioning biodegradable plastics and related keywords were analyzed. A total of 4,403 articles were identified, with a peak in coverage in 2021 followed by a slight decline. Keyword analysis revealed a focus on "eco-friendly" materials like PHA and PLA, and concepts like recycling and commercialization. Media attention toward biodegradable plastics significantly increased, reflecting growing public awareness of sustainable alternatives to conventional plastics. However, challenges such as degradation conditions, waste management integration, and economic feasibility require further attention.

TCohPrompt: task-coherent prompt-oriented fine-tuning for relation extraction

Prompt-tuning has emerged as a promising approach for improving the performance of classification tasks by converting them into masked language modeling problems through the insertion of text templates. Despite its considerable success, applying this approach to relation extraction is challenging. Predicting the relation, often expressed as a specific word or phrase between two entities, usually requires creating mappings from these terms to an existing lexicon and introducing extra learnable parameters. This can lead to a decrease in coherence between the pre-training task and fine-tuning. To address this issue, we propose a novel method for prompt-tuning in relation extraction, aiming to enhance the coherence between fine-tuning and pre-training tasks. Specifically, we avoid the need for a suitable relation word by converting the relation into relational semantic keywords, which are representative phrases that encapsulate the essence of the relation. Moreover, we employ a composite loss function that optimizes the model at both token and relation levels. Our approach incorporates the masked language modeling (MLM) loss and the entity pair constraint loss for predicted tokens. For relation level optimization, we use both the cross-entropy loss and TransE. Extensive experimental results on four datasets demonstrate that our method significantly improves performance in relation extraction tasks. The results show an average improvement of approximately 1.6 points in F1 metrics compared to the current state-of-the-art model. Codes are released at https://github.com/12138yx/TCohPrompt.

Analisis Media Monitoring dan Jaringan Program Lapak Ganjar untuk Mendukung Pemasaran Digital bagi UMKM

Lapak Ganjar is a program launched by the Governor of Central Java Ganjar Pranowo since July 2020 to help promote commodities for Central Java MSMEs, especially when facing economic challenges during the ongoing Covid-19 pandemic, via Instagram @lapak_ganjar. This program is developing to support digital marketing for MSMEs, not only MSMEs in Central Java, but also MSMEs in several other provinces. This research aims to describe the analysis of media monitoring and network of the Lapak Ganjar program to support digital marketing for MSMEs. Several relevant concepts are used in this research, including the concepts of digital marketing and electronic word of mouth (e-WOM). This type of research is quantitative descriptive with media monitoring and network analysis methods using brand24 and netlytic. Media monitoring analysis was carried out in the period June to July 2022. The results of media monitoring analysis via brand24 in that period revealed that the Lapak Ganjar program received positive sentiment from netizens, while Twitter analysis using Netlytic in June to July 2022 found a total of 2,013 tweets mentioning the word Lapak Ganjar with some relevant related keywords. Network analysis via Netlytic also displays cluster 1 which refers to the account most frequently referred to, namely the ganjaranapps account.

Digital Battlegrounds: The Interplay of Social Media, State Power, and Influencers in Türkiye’s Earthquake Response

This study examines the critical role of Twitter (X) in crisis communication during the earthquake that struck Türkiye on 6 February 2023, focusing on how two prominent influencers, Haluk Levent and Oğuzhan Uğur, effectively utilized the platform in response to the disaster. Analysis of highly retweeted posts and engagement rates for tweets collected using related keywords—“ahbap,” “babalatv,” “haluklevent,” and “oguzhanugur”—reveals how Twitter served not only for functions such as sharing locations for rescue operations, information dissemination, organization, and fundraising but also for defense against attacks and criticism of the government. Furthermore, Twitter emerged as a digital battleground where power struggles unfolded between the state and activist influencers. This study addresses this oversight by examining how Twitter functions not merely as a tool for communication and aid coordination but also as an arena of political contestation, filling a critical gap in understanding the role of social media. It underscores the critical need to consider the underlying political dynamics that social media interactions bring to the forefront during emergencies.

Using Knowledge Graphs to Analyze the Characteristics and Trends of Forest Carbon Storage Research at the Global Scale

Research on forest carbon storage (FCS) is crucial for the sustainable development of human society given the context of global climate change. Previous FCS studies formed the science base of the FCS field but lacked a macrolevel knowledge summary. This study combined the scientometric mapping tool VOSviewer and multiple statistical models to conduct a comprehensive knowledge graph mining and analysis of global FCS papers (covering 101 countries, 1712 institutions, 5435 authors, and 276 journals) in the Web of Science database as of 2022, focusing on revealing the macro spatiotemporal pattern, multidimensional research status, and topic evolution process of FCS research at the global scale, so as to grasp the status of global FCS research more clearly and comprehensively, thereby facilitating the future decision-making and practice of researchers. The results showed the following: (1) In the past three decades, the number of FCS papers indicated an increasing trend, with a growth rate of 4.66/yr, particularly significant after 2010. These papers were mainly from Europe, the Americas, and Asia, while there was a huge gap between Africa, Oceania, and the above regions. (2) For the research status at the national, institutional, scholar, and journal levels, the USA, with 331 FCS papers and 18,653 total citations, was the most active and influential country in global FCS research; the United States Forest Service topped the influential ranking with 4115 citations; Grant M. Domke and Jerome Chave were the most active and influential FCS researchers globally, respectively. China’s activity (237 papers) and influence (5403 citations) ranked second, and the Chinese Academy of Sciences was the most active research institution in the world. Currently, FCS research is published in a growing number of journals, among which Forest Ecology and Management ranked first in the number of papers (154 papers) and citations (6374 citations). (3) In recent years, the keyword frequency of monitoring methods, driving factors, and reasonable management for FCS has increased rapidly, and many new related keywords have emerged, which means that researchers are not only focusing on the estimation and monitoring of FCS but also increasingly concerned about its driving mechanism and sustainable development.

Neuropsychological Diagnosis and Assessment of Alexia: A Mixed-Methods Study.

The neuropsychological diagnosis and assessment of alexia remain formidable due to its multifaceted presentations and the intricate neural underpinnings involved. The current study employed a mixed-method design, incorporating cluster and thematic analyses, to illuminate the complexities of alexia assessment. We used the Web of Science and Scopus to retrieve articles spanning from 1985 to February 2024. Our selection was based on identified keywords in relation to the assessment and diagnosis of alexia. The analysis of 449 articles using CiteSpace (Version 6.3.R1) and VOSviewer (Version 1.6.19) software identified ten key clusters such as 'pure alexia' and 'posterior cortical atrophy', highlighting the breadth of research within this field. The thematic analysis of the most cited and recent studies led to eight essential categories. These categories were synthesized into a conceptual model that illustrates the interaction between neural, cognitive, and diagnostic aspects, in accordance with the International Classification of Functioning, Disability, and Health (ICFDH) framework. This model emphasizes the need for comprehensive diagnostic approaches extending beyond traditional reading assessments to include specific tasks like character identification, broader visual processing, and numerical tasks. Future diagnostic models should incorporate a diverse array of alexia types and support the creation of advanced assessment tools, ultimately improving clinical practice and research.

Emerging trends in neuromodulation for schizophrenia: a global bibliometric analysis

The utilization of neuromodulation techniques is increasingly capturing the attention of researchers and clinicians as potential non-pharmaceutical interventions for treating schizophrenia, especially among drug-resistant schizophrenia patients. Assessing the existing landscape of research activity and identifying gaps in neuromodulation-schizophrenia research is crucial for strategic planning and guiding future research in this domain. This bibliometric analysis paper aims to discern the publications and research trends in neuromodulation schizophrenia studies spanning 2019 to 2023. The Scopus database search was performed using the related keywords. Neuromodulation-schizophrenia-related publications were retrieved from the Scopus database from 2019 to 2023. Bibliometric analyses were performed using Harzing's Publish or Perish, Microsoft Excel and VOS viewer software programs. Three hundred fifty-three publications from the Scopus database were retrieved and analyzed to answer the research questions. The highest number of publications, 87, was observed in 2022. The United States led the way in publishing neuromodulation schizophrenia research with 96 articles. Keyword analysis revealed that "transcranial direct current stimulation" (tDCS) and "transcranial magnetic stimulation" (TMS) were the most prevalent neuromodulation techniques investigated in schizophrenia research. Transcranial-focused ultrasound (TUS) emerged as a novel and current neuromodulation technique explored in treating schizophrenia, as indicated by the analysis of selected journal articles. This bibliometric paper provides insights into the current status, knowledge base, and future directions of neuromodulation-schizophrenia studies, which will serve future researchers in focusing on applying neuromodulation techniques as potential non-pharmaceutical interventions for schizophrenia.

Effect of near-infrared spectroscopy on postoperative delirium in cardiac surgery with cardiopulmonary bypass: a systematic review and meta-analysis.

Postoperative delirium (POD) is a common anesthetic side effect in cardiac surgery. However, the role of oxygen saturation monitoring in reducing postoperative delirium has been controversial. Therefore, this meta-analysis aimed to analyze whether NIRS monitoring during cardiac surgery under cardiopulmonary bypass could reduce the incidence of postoperative delirium. PubMed, Web of Science, Cochrane Library, Embase and China National Knowledge Infrastructure (CNKI) databases were systematically searched using the related keywords for randomized-controlled trials (RCTs) published from their inception to March 16, 2024. This review was conducted by the Preferred Reporting Project and Meta-Analysis Statement (PRISMA) guidelines for systematic review. The primary outcome was postoperative delirium, and the second outcomes included the length of ICU stay, the incidence of kidney-related adverse outcomes, and the incidence of cardiac-related adverse outcomes. The incidence of postoperative delirium could be reduced under the guidance of near-infrared spectroscopy monitoring (OR, 0.657; 95% CI, 0.447-0.965; P = 0.032; I2 = 0%). However, there were no significant differences in the length of ICU stay (SMD, 0.005 days; 95% CI, -0.135-0.146; P = 0.940; I2 = 39.3%), the incidence of kidney-related adverse outcomes (OR, 0.761; 95% CI, 0.386-1.500; P = 0.430; I2 = 0%), and the incidence of the cardiac-related adverse outcomes (OR, 1.165; 95% CI, 0.556-2.442; P = 0.686; I2 = 0%) between the two groups. Near-infrared spectroscopy monitoring in cardiac surgery with cardiopulmonary bypass helps reduce postoperative delirium in patients. PROSPERO, identifier, CRD42023482675.

Emerging Themes and Research Frontiers in Suicide Prediction: A Scientometric Analysis.

Suicide remains a critical global health issue despite advancements in mental health treatment.The purpose of this analysis is to emphasize the development, patterns, and noteworthy outcomes of suicide prediction research. It also helps to uncover gaps and areas of under-researched topics within suicide prediction. A scientometric analysis was conducted using Biblioshiny and VOSviewer. To thoroughly assess the academic literature on suicide prediction, various scientometric methodologies such as trend analysis and citation analysis were employed. We utilized the temporal features of the Web of Science to analyze publication trends over time. Author affiliation data were used to investigate the geographic distribution of research. Cluster analysis was performed by grouping related keywords into clusters to identify overarching themes within the literature. A total of 1,703 articles from 828 different sources, spanning from 1942 to 2023, were collected for the analysis. Machine learning techniques might have a big influence on suicide-related event prediction, which would enhance attempts at suicide prevention and intervention. The conceptual understanding of suicide prediction is enhanced by scientometric analysis, which further uncovers the research gap and literature in this area. Suicide prediction research underscores that suicidal behavior is not caused by a single factor but is the result of a complex interplay of multiple factors. These factors may include biological, psychological, social, and environmental factors. Understanding and integrating these factors into predictive models is a theoretical advancement in the field. Unlike previous bibliometric studies in the field of suicide prediction that have typically focused on specific subtopics or data sources, our analysis offers a comprehensive mapping of the entire landscape. We encompass a wide range of suicide prediction literature, including research from medical, psychological, and social science domains, thus providing a holistic overview.

Publication Trends in Osteoporosis Treatment: A 20-Year Bibliometric Analysis.

Osteoporosis prevalence continues to escalate with the growth of the older adult population. In this study, we aimed to investigate the profile of osteoporosis treatment-related research articles published in the past 20 years using bibliometric analysis. We analyzed all osteoporosis treatment-related articles published between 2001 and 2020 in the Web of Science (WoS) database using bibliometric methods. In the Title search section in WoS, we searched the documents using "osteoporosis treatment"-related keywords. We used the VOSviewer software to construct the bibliometric maps of keyword co-occurrences. Our search yielded 29,738 publications, 21,556 (72.5%) were original articles and 4,529 (15.2%) were review articles and review articles (4,529). We noticed a steady increase in the publication numbers from 2001 to 2020. The overall scientific publication number in WoS increased 3.5-fold, with the five most productive countries being the USA, China, Germany, the United Kingdom, and Japan. The largest contributor was the University of California system. The most productive journals were Osteoporosis International (1,679, 6.4%), Bone (832, 3.2%), and the Journal of Bone and Mineral Research (727, 2.8%). We observed increasing trends in the appearance of denosumab and teriparatide during the last two decades. In our keyword co-occurrence analysis, we constructed four keyword clusters using VOSviewer. In this study, we provided a gross overview of the visibility and productivity of research studies in osteoporosis treatment. Substantial changes have occurred in osteoporosis treatment over the last 20 years. The effector mechanism of anti-osteoporosis medications could be future hot spots in osteoporosis research. We believe that our study is a valuable guide for clinicians related to the global outputs of osteoporosis treatment.

Association of Dietary Vegetable and Fruit Consumption with Sarcopenia: A Systematic Review and Meta-Analysis.

Previous studies have shown contradictory results regarding the association between vegetable and fruit consumption and the risk of sarcopenia. We aimed to evaluate this association using a meta-analysis, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. We searched PubMed, EMBASE, and the Cochrane Library through July 2023 using related keywords. Pooled odds ratios (ORs) with 95% confidence intervals (CIs) were calculated based on the random-effects model. We included 14 observational studies with 11 cross-sectional and three cohort studies involving 6436 sarcopenias among 33,801 participants. Vegetable and fruit consumption were significantly associated with reduced sarcopenia risk (OR, 0.61; 95% CI, 0.48 to 0.79; I2 = 59.8%). The association was significant in cross-sectional studies (OR, 0.64; 95% CI, 0.49 to 0.84; I2 = 56.3%; n = 11) but not in cohort studies (OR, 0.50; 95% CI, 0.22 to 1.11; I2 = 76.4%; n = 3). Moreover, the association was significant in age ≥60 (OR, 0.64; 95% CI, 0.49 to 0.83; I2 = 58.0%; n = 10). This meta-analysis suggests that eating vegetables and fruit reduces sarcopenia risk. However, as cohort studies provide a higher level of evidence than case-control studies, further prospective cohort studies should be conducted.

Cytotoxic Effects of Plant Bioactive Compounds on T47d Breast Cancer Cells Line: A Review

The continuous cell line known as T47D cells originates from the isolation of epithelial cells from the ductal breast tissue of a 54-year-old woman with metastatic breast cancer. Numerous plant species have been employed in alternative anti-breast cancer therapy, showing advancements in recent years. The aim of this systematic review is to assess the potential bioactive compounds from herbal plant extracts and analyze the effects of herbal plants on T47D breast cancer cells. This research employs a systematic approach to gather articles, encompassing related research questions, chosen databases, keyword selection, inclusion and exclusion criteria, as well as outcomes and conclusions regarding the collected articles. From the reviewed articles, several plants exhibit anti-breast cancer activity on T47D cell lines, namely Calamintha incana, Sterculia quadrifida, Psidium guajava, Uncaria nervosa, Syzygium aqueum, Capsicum annum, Bauhinia scandens, Lansium domesticum, and Garcinia cowa due to their content of bioactive compounds such as triterpenoids, alkaloids, phenolics, flavonoids, saponins, and tannins. These bioactive compounds from the plants exert significant influence on cell cycle, proliferation, fatty acid synthesis, and apoptosis of cancer cells.

Global status and trends of metabolomics in diabetes: A literature visualization knowledge graph study.

Diabetes is a metabolic disease characterized by hyperglycemia, which has increased the global medical burden and is also the main cause of death in most countries. To understand the knowledge structure of global development status, research focus, and future trend of the relationship between diabetes and metabolomics in the past 20 years. The articles about the relationship between diabetes and metabolomics in the Web of Science Core Collection were retrieved from 2002 to October 23, 2023, and the relevant information was analyzed using CiteSpace6.2.2R (CiteSpace), VOSviewer6.1.18 (VOSviewer), and Bibliometrix software under R language. A total of 3123 publications were included from 2002 to 2022. In the past two decades, the number of publications and citations in this field has continued to increase. The United States, China, Germany, the United Kingdom, and other relevant funds, institutions, and authors have significantly contributed to this field. Scientific Reports and PLoS One are the journals with the most publications and the most citations. Through keyword co-occurrence and cluster analysis, the closely related keywords are "insulin resistance", "risk", "obesity", "oxidative stress", "metabolomics", "metabolites" and "biomarkers". Keyword clustering included cardiovascular disease, gut microbiota, metabonomics, diabetic nephropathy, molecular docking, gestational diabetes mellitus, oxidative stress, and insulin resistance. Burst detection analysis of keyword depicted that "Gene", "microbiota", "validation", "kidney disease", "antioxidant activity", "untargeted metabolomics", "management", and "accumulation" are knowledge frontiers in recent years. The relationship between metabolomics and diabetes is receiving extensive attention. Diabetic nephropathy, diabetic cardiovascular disease, and kidney disease are key diseases for future research in this field. Gut microbiota, molecular docking, and untargeted metabolomics are key research directions in the future. Antioxidant activity, gene, validation, mass spectrometry, management, and accumulation are at the forefront of knowledge frontiers in this field.

CAR-NK Cells as Promising Immune Therapeutics: Platforms and Current Progress

Context: Adoptive T-cell therapy with chimeric antigen receptor (CAR) has shown tremendous progress in hematological cancers. However, some obstacles, such as high price tag, cytokine release syndrome, inability to penetrate solid tumors, and manufacturing complexity limit the wide application of this therapy. Natural killer (NK) cells can kill target cells via mechanisms similar to those of CD8+ cytotoxic T cells; therefore, CAR-NK cell therapy is a promising strategy for cancer treatment. Evidence Acquisition: In this manuscript, all articles published in English regarding CAR-NKs and their application for the treatment of different types of cancers were collected from several databases, including PubMed, Scopus, and Google Scholar, using related keywords such as "Cancer, CAR construction, NK cells, and CAR-NK cells". Results: Compared with CAR-T cells, CAR-NK cells have several advantages, including less toxicity, a high potential opportunity for universal off-the-shelf manufacturing, increased infiltration into solid tumors, overcoming resistant tumor microenvironment, and absence of graft-versus-host disease (GVHD). Conclusions: In this review, we discuss NK cell biology, the source of CAR-NK cells, CAR structure, advances, challenges, and ways to overcome these challenges in CAR-NK cell therapy. Furthermore, we have summarized and highlighted some preclinical and clinical studies in this field.

The Process of Validating a Persian Version of Addiction Potential Scale for Children in the Iranian Population: A Systematic Review.

Hitherto, no instrumental research has been designed to measure the addiction potential for children in Iran. Therefore, the questionnaires designed to investigate addiction were examined in this systematic review article. In the present systematic review, all Iranian and foreign research on addiction potential for children were examined until March 2022. Using separate keywords and their Latin synonyms according to Mesh terms, an extensive search was conducted in databases: PubMed, Magiran, Iranmedex, Medline, Google Scholar, SID, and Irandoc. In total, 173 Farsi and English papers were included in the initial list, and after evaluation according to the Meta-analysis of Observational Studies in Epidemiology (MOOSE) checklist and acceptance criteria, 43 final papers were selected for systematic review. Through searching in Persian and English databases and using related keywords, 173 papers were found in the initial search and after removing duplicates and unrelated studies, 43 papers were selected for systematic review. In this research, papers related to the addiction potential between 1998 and 2019 were considered, and among these, 22 papers particularly dealt with addiction. In the conducted studies, the awareness, attitude, talent, and factors affecting addiction were mostly measured and in some papers, addiction potential was measured. Designing psychometrically appropriate tools is necessary to measure the addiction potential of children in Iran. Due to the unavailability of appropriate tools and the fact that the previous versions are not up to date and are not checked regularly, for better and more complete decision-making in the health policy-making process more investigation in this field is necessary.

Covering artificial intelligence: the role of European Union, British, and American media outlets in generative AI Visibility

Artificial intelligence (AI) has emerged as one of the central topics of 2023 with extensive media coverage of the most relevant technologies and issues associated with this subject. In a highly competitive digital media landscape, search engine optimization (SEO) has become cybermedia’s primary strategy to increase visibility and attract more readers. The objective of this paper is to analyze the visibility of content published by the media relating to artificial intelligence, focusing on a selection of related keywords. The research also aims to investigate how this visibility has impacted both the technologies themselves and the analyzed media outlets. A total of 69 media outlets from 12 European Union countries, the United States, and the United Kingdom were examined. The results reveal a pronounced dominance of U.S. media, closely followed by Spanish media. There is an uneven distribution of media outlets across most of the countries analyzed, with two or three most of the of visibility. The search queries that contribute the most visibility to the analyzed media align with an informational intent, are of the long-tail type, and are associated with OpenAI technologies, particularly ChatGPT. Moreover, these queries are primarily found in news sections dedicated to science and technology. The findings underscore both the increasing interest in the subject and the effective SEO practices of certain media outlets.

Machine Learning and Deep Learning Sentiment Analysis Models: Case Study on the SENT-COVID Corpus of Tweets in Mexican Spanish

This article presents a comprehensive evaluation of traditional machine learning and deep learning models in analyzing sentiment trends within the SENT-COVID Twitter corpus, curated during the COVID-19 pandemic. The corpus, filtered by COVID-19 related keywords and manually annotated for polarity, is a pivotal resource for conducting sentiment analysis experiments. Our study investigates various approaches, including classic vector-based systems such as word2vec, doc2vec, and diverse phrase modeling techniques, alongside Spanish pre-trained BERT models. We assess the performance of readily available sentiment analysis libraries for Python users, including TextBlob, VADER, and Pysentimiento. Additionally, we implement and evaluate traditional classification algorithms such as Logistic Regression, Naive Bayes, Support Vector Machines, and simple neural networks like Multilayer Perceptron. Throughout the research, we explore different dimensionality reduction techniques. This methodology enables a precise comparison among classification methods, with BETO-uncased achieving the highest accuracy of 0.73 on the test set. Our findings underscore the efficacy and applicability of traditional machine learning and deep learning models in analyzing sentiment trends within the context of low-resource Spanish language scenarios and emerging topics like COVID-19.