Word Frequency Research Articles

Automatic categorization of medical documents in Afaan Oromo using ensemble machine learning techniques

Automatic medical document classification using machine learning techniques can enhance the productivity of healthcare services by reducing processing time and cost. This work proposes an ensemble learning approach to develop a model that classifies electronic medical documents in Afaan Oromo. The main tasks in this work are preparing the corpus, pre-processing, training the models, and the classification process. We used the term frequency-inverse document frequency (TF-IDF) and bag of words (BOW) feature extraction methods. An ensemble technique in this work is that it creates multiple individual classifier predictions from naïve Bayes, random forest, SVM, and logistic regression and then combines them to advance a reliable and more accurate classifier. Evaluation measures were employed using accuracy, F1-score, recall, and precision for performance comparison. The efficiency of the proposed method is compared with the two existing boosting approaches, namely gradient boosting and adaboost. The experimental result shows the efficiency of BOW feature extraction over TF-IDF in this work on our dataset. These results also illustrated the effectiveness of the proposed model by scoring 94.81% accuracy and 94.84% F1-score. This work significantly contributes to the technological enhancement of service delivery, managing documents through classification methods, and advancing the data processing systems in healthcare sectors.

Do physicians and patients speak different languages: quantitative evidence from linguistic analysis

Abstract Background Misunderstanding and miscommunication between physicians and patients are well-accepted sources of poor therapy adherence and poor outcomes. Some of these issues are suspected to occur because these two groups speak different "languages". A likely component of such language difference is vocabulary; specifically, the use of medical terminology. Nonetheless, there are other psychological aspects of language such as authoritative and emotional use. The text analysis programme, Linguistic Inquiry Word Count (LIWC), was used to assess such features. LIWC is an established tool that analyses the frequency of words that fall into various linguistic, psychological, and emotional categories. The aim was to compare text from both physicians and patients. The context was the use of anticoagulation therapy in patients with atrial fibrillation. Methods Three articles from English-speaking countries (Australia, Canada, and the UK) were examined. These articles presented transcribed verbal communications between interviewers and groups of physicians and patients. More than 80 separate comments, each ≥ 20 words, made by each group were extracted from the articles and analysed. The total number of words was 8,609 from physicians and 4,804 from patients. Data were collected for the following LIWC analysis categories: (1) the proportion of big words (words with ≥7 letters), (2) clout; high scores suggest that the speaker is confident, authoritative, and has a high level of social dominance. It implies that the individual is speaking from a position of strength or influence; and (3) emotion: this category is integral to understanding how people communicate feelings and emotions. Results As anticipated the number of big words was higher in physician interviews (19±1%) than for patients (12±1%; P=0.0013). The clout indicator also showed the physicians with a higher score (43±6 vs 16±6; P=0.028). In contrast, in the emotion category, patient scores (1.19±0.02) were higher than for physicians (0.58±0.15; P=0.016); primarily because of a three-fold higher negative emotion score (0.53±0.08 vs 0.16±0.11; P=0.048). Conclusions Physicians and patients used language differently. As expected, vocabulary differed; physicians used more big words. This is consistent with greater use of medical terminology, a known source of miscommunication. The higher physician clout score indicates the potential for a power imbalance. The greater use of emotion-related words by patients is consistent with their anxiety and concern. Human judgment and contextual analysis are required to fully understand and address the nuances of communication and associated understanding. Nevertheless, LIWC can play a supportive role. If we identify language patterns likely to result in miscommunication or misunderstanding, steps can be taken to mitigate the effects. LIWC provided quantitative insight into qualitative impressions and revealed subtle, but potentially vital, differences.

Mapping The Growth of ESG Research: A Bibliometric Analysis Using Bradford's, Lotka's, and Zipf's Laws

Objective: The objective of this study is to investigate the growth and development of research on Environmental, Social, and Governance (ESG) factors using bibliometric analysis. The aim is to understand the publication trends in ESG research and identify influential authors, key themes, and opportunities for future studies. Theoretical Framework: The research is grounded in key bibliometric laws such as Bradford's law (journal productivity), Lotka's law (scientific productivity of authors), and Zipf's law (word frequency analysis). These laws form the basis of the study and provide a solid framework for understanding the evolution of ESG research. Method: This study adopts a bibliometric analysis approach, using data from the Web of Science and Scopus databases. A total of 699 articles from 345 journals and 1,574 authors were analyzed. Techniques like citation analysis, co-citation analysis, bibliographic coupling, and network analysis were employed to assess publication patterns and collaborations. Data was processed using R software and Bibliometrix. Results and Discussion: The results reveal a significant increase in ESG-related publications, particularly after 2013, with annual growth of 39.97%. The study identifies influential authors, such as Hebbe and Buallay, and explores the themes of sustainability, corporate social responsibility, and governance. In the discussion, the results are contextualized within the broader ESG framework, highlighting the role of ESG in corporate behavior and investment strategies. Research Implications: The study provides insights into how ESG research can inform policy-making and corporate decision-making. The findings highlight the importance of ESG factors in sustainable development and suggest future research avenues in areas like digital transformation, entrepreneurship, and innovation. Originality/Value: This study contributes to the literature by offering a comprehensive overview of ESG research, utilizing innovative bibliometric techniques to track its evolution. The originality lies in the use of multiple bibliometric laws to analyze ESG trends, making it valuable for researchers and practitioners looking to understand current and future directions in ESG.

Information to the Population About COVID-19 in the First Year of the Pandemic: Case Study on the Portal of the Health Department of Campina Grande, Paraíba, Brazil

Objective: To analyze the risk communication about the COVID-19 pandemic carried out on the website of the Health Department of Campina Grande, Paraíba, Brazil. Theoretical Framework: Risk communication in public health emergencies, according to the WHO guideline for policy and practice of this health communication in crises. Method: Qualitative study, focused on the content analysis of the publications made on the website of the Health Department of Campina Grande, Paraíba, from March 2020 to December 2021. Results and Discussion: The Health Department of Campina Grande, Paraíba, effectively used its website to disseminate information about the COVID-19 pandemic, such as social isolation measures and partial lockdown in areas with a high incidence of cases; sanitary barriers to monitor symptoms and control circulation; the installation of a field hospital, expansion of testing in Basic Health Units and distribution of masks and hygiene kits in vulnerable areas. The most frequent words on the portal in 2022 were “pandemic”, “mask” and “coronavirus”, in daily updates, guidelines on prevention measures, service protocols, decrees and restrictions, education and awareness and vaccination campaign at the end of the year. Research Implications: There was publication of accurate and accessible information, publication of administrative acts, positive culture in public health and, therefore, these actions demonstrate a significant effort by the Campina Grande Health Department to use digital communication to face the COVID-19 pandemic in accordance with the UN guideline. However, it was observed that in terms of clarity, some messages used technical terms that may have made it difficult for less educated audiences to understand. The portal did not provide accessible versions for people with visual impairments. Originality/Value: This study contributes to demonstrating that during the pandemic, the Campina Grande Health Department portal was an essential tool for residents of Campina Grande-PB in a practical and accessible way, with constant updates, disseminating information on the progress of the disease, vaccination campaigns and preventive measures, such as the use of masks and social distancing, with potential contribution to the implementation of preventive measures and adherence to vaccination. It is suggested that there could be greater accessibility for people with less education and sensory disabilities.

A Method for Measuring Word Sequence Complexity of Text

ABSTRACT In linguistics and natural language processing, measuring text features is crucial for representing and revealing the properties of texts in terms of topics, genres, sentiment and more. Current methods predominantly rely on the frequency of linguistic units and rarely consider the syntagmatic properties of these units, which can reflect deeper linguistic characteristics (e.g. syntax and pragmatics). This paper proposes a general method for calculating the sequence complexity of text. By combining the features of word length and word frequency, two specific implementations of this method are provided. Using these two formulas, word sequence complexity of text based on the Brown Corpus and the Gutenberg Corpus is calculated. The results show that word sequence complexity of text indicates a characteristic of gradual stabilization. By comparing random texts with natural texts, it is found that word sequence complexity is influenced by syntactic rules rather than sentence order, and natural texts tend to alternate between words of varying lengths and frequencies. Classification experiment results indicate that the proposed word sequence complexity outperforms commonly used quantitative indicators for representing the genre of text, such as TTR, information entropy, Zipf’s law parameters and motifs.

More than words: can free reports adequately measure the richness of perception?

The question of the richness (or sparseness) of conscious experience has evoked ongoing debate and discussion. Claims for both richness and sparseness are supported by empirical data, yet they are often indirect, and alternative explanations have been put forward. Recently, it has been suggested that current experimental methods limit participants' responses, thereby preventing researchers from assessing the actual richness of perception. Instead, free verbal reports were presented as a possible way to overcome this limitation. As part of this approach, a novel paradigm of freely reported words was developed using a new metric, intersubjective agreement (IA), with experimental results interpreted as capturing aspects of conscious perception. Here, we challenge the validity of freely reported words as a tool for studying the richness of conscious experience. We base our claims on two studies (each composed of three experiments), where we manipulated the richness of percepts and tested whether IA changed accordingly. Five additional control experiments were conducted to validate the experimental logic and examine alternative explanations. Our results suggest otherwise, presenting four challenges to the free verbal report paradigm: first, impoverished stimuli did not evoke lower IA scores. Second, the IA score was correlated with word frequency in English. Third, the original positive relationship between IA scores and rated confidence was not found in any of the six experiments. Fourth, a high rate of nonexisting words was found, some of which described items that matched the gist of the scene but did not appear in the image. We conclude that a metric based on freely reported words might be better explained by vocabulary conventions and gist-based reports than by capturing the richness of perception.

Inclusive education in Sweden

Background and aim: Teachers’ positive attitudes towards inclusive education are taken to be critical to providing education that better meets pupils’ learning. Studies have therefore tried to clarify interaction between teachers’ attitudes and inclusive education. The present study reports data on teachers’ attitudes, self-efficacy and collaboration towards inclusive education in Sweden. Nation-wide data were collected from teachers before they joined a national professional development programme aimed at strengthening schools' competence in adapting teaching to the conditions and needs of pupils. Methods: Participants were 2,348 (51,6%) out of 4,553 targeted teachers that answered an online survey. The survey included three instruments: the Ohio State Teacher Efficacy Scale (OSTES), the Sentiments, Attitudes and Concerns about Inclusive Education – Revised (SACIE-R), and bespoke questions about teachers’ attitudes towards collegial learning (TACL). Mean values and correlations were assessed. Responses to an open question about teachers’ expectations ahead of starting their training programme were analyzed in NVivo, using word frequency analysis. Results: Three-quarters of respondents show overall positive responses towards adapting their teaching to the conditions and needs of pupils. However, almost two-thirds of teachers do also report significant concerns about their ability to do inclusive education well. Scores remained largely unaffected by public or private school ownership, nor did the affluence of school catchment areas affect teacher scores. Conclusions: The self-reported attitudes, self-efficacy and collaboration among teachers in Sweden towards adapting their teaching to the conditions and needs of pupils support positive research conclusions: although they do have concerns likely to be founded on professional considerations, teachers are by and large positive about meeting pupils’ learning needs.

Pronouns in Welcome: Linguistic Construction of Student Identity in Chinese University Banners

This study explores the nuanced role of pronoun usage in welcome banners at Chinese universities and examines its influence on freshmen’s identity construction within the cultural context of China. Employing a systematic collection and analysis of a corpus of welcome banners, the research utilizes corpus analysis and word frequency statistics to investigate how pronoun choices shape and reinforce freshmen’s sense of identity. The findings highlight the significant impact of linguistic subtleties on the orientation activities at Chinese universities, influencing freshmen’s social integration and identity formation. By illuminating the linguistic characteristics of Chinese welcome banners, this research provides empirical evidence of how cultural and linguistic contexts affect student identity through orientation activities. This study contributes to a deeper understanding of the intersection between language, culture, and identity in higher education.

Evidence of community structure in phonological networks of multiple languages.

Thousands of phonological word forms known to a speaker can be organised as a lexical network using the tools of network science. In these networks, nodes represent words and edges are placed between phonological neighbours. Previous work has shown that phonological networks of various languages have similar macrolevel network properties. The present study aimed to investigate if phonological networks of different languages also have similar mesolevel properties, specifically, the presence of robust community structure. Prior community detection analyses revealed robust community structure for English. Community detection analyses conducted on French, German, Dutch, and Spanish networks indicate that all networks showed strong evidence of community structure-mesolevel clustering of word forms whereby larger communities tended to contain shorter, frequent words with many phonological neighbours. Words of the same community tended to share similar phonotactic structures. Results suggest that the organisation of phonological word forms in language are governed by similar principles that could have important implications for lexical processing. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Life values in Russia and China: Semantic analysis and comparison

The paper seeks to explore the core life values of people living in Russia and China using an online survey in the respondents’ native languages with samples of 887 and 559 participants from each country respectively, who were asked to think of three words associated ‘with something most important in life’. The word-association arrays were translated into English by an automatic translator; then we compared the frequencies of individual words or those of their meanings obtained using the Roget’s Thesaurus. The words ‘family’ and ‘love’ were the most frequent in both samples, but the frequencies of these and most of the other words from the semantic core of each sample differed significantly. Analyses at the level of semantic vectors showed that more than half of the meanings that Russian respondents described as important and more than a third of the meanings important to the Chinese respondents had significant differences in frequencies between the samples. The paper presents 62 semantic groups of the Roget’s Thesaurus, the frequencies of which are reliably different; these are the meanings in which the Chinese and Russian samples differ with regard to life values. There are also 26 semantic groups, the frequencies of which are statistically the same and comparatively high in both samples: these are the common meanings. The results may be used in the design of automatic and AI systems to reduce the intercultural barriers.

The more proficient the learners, the less sophisticated their L2 vocabulary?

Abstract Mean-frequency scores of lexical sophistication are used to evaluate written and spoken language production. They are calculated using word frequencies extracted from a reference corpus. Using mixed-effects regression models, we analyse the strength of the relationship between L2 proficiency and mean-frequency scores in spoken and written texts using reference corpora representing different modes and registers. We control for task and topic effects. We observe that mean-frequency measures of lexical sophistication are considerably more influenced by the mode and register of the reference corpus used to calculate these scores than by language users’ proficiency level. Advanced language users produce more frequent vocabulary, typical of the target register, in both spoken monologues and written essays. These results provide evidence in favour of a conceptual and terminological shift from lexical sophistication to register appropriateness (as suggested by Durrant & Brenchley, 2019) to refer to the construct captured by mean-frequency scores of vocabulary use.

A Graphic Review of Studies on Ocean and Mediterranean Sea Environment Quality

With so many studies today on the water quality of the sea, one can hardly comprehend the multitude of topics that arise all over the world. This study provides a few graphic syntheses related to the most frequent words (including their clustering and links), trend topics, the spatial distribution of the researched areas, and the thematic evolution of the research directions over the decades. The most frequent authors’ keywords have a 50% similitude between the ocean studies and the studies related to the Mediterranean Sea; these keywords are part of a causal chain that dominates the marine studies on water quality: nutrients → eutrophication → phytoplankton → chlorophyll → seagrass. The most frequent words in the titles and abstracts of the selected papers from the Web of Science are “concentration” and “species”; in the Mediterranean studies, “chlorophyll” and “temperature” are the most frequent. In close connection with water quality, Zostera marina (eelgrass) and Crassotrea virginica (eastern oyster) prevail at the global scale, while Posidonia oceanica (Neptune grass) is relevant in the Mediterranean space. Some of the most studied water bodies are the South China Sea, San Francisco Bay, Chesapeake Bay, and, in the Mediterranean Sea, the Adriatic, Ionian, Aegean, and Marmara seas. “Climate change” and “remote sensing” are trend topics that shape the current studies on water quality; the increasing sea surface temperature enhances algal blooms—these need to be monitored using satellite imagery for the sustainable evolution of human activities, including aquaculture.

Top-down feedback normalizes distortion in early visual word recognition: Insights from masked priming.

The identification of visually presented words tolerates distortions in the input format, as Hannagan et al. Plos One, 7, e32121, (2012) demonstrated in a masked priming lexical decision task, showing sizable identity-priming effects with CAPTCHA-like primes. This tolerance to distortion has two potential explanations: bottom-up normalization in the encoding stage (Dehaene et al., Trends in Cognitive Sciences, 9, 335-341, 2005) or top-down lexical feedback (McClelland & Rumelhart, Psychological Review, 88, 375-407, 1981). To disentangle the predictions of these accounts, we conducted two masked identity-priming experiments with printed and CAPTCHA-like distorted primes on high- and low-frequency words. The rationale was that, in the distorted format, high-frequency words would benefit more from top-down feedback than low-frequency words. Results in the lexical decision experiment showed that, for high-frequency words, identity-priming effects were only slightly greater for printed than for CAPTCHA-like primes, whereas this difference was larger for low-frequency words. In contrast, when employing the same-different matching task, which does not require lexical access, the identity-priming effect was greater for printed primes and was unaffected by word frequency. Thus, during lexical access, top-down feedback may help normalize the visual input in the early stages of word recognition, challenging bottom-up models of visual word recognition.

Tribute VS "Nanman": The Image Construction of "Magic Mirror Type"

For over 2000 years, feudal dynasties throughout China have referred to southerners as the “Nanman” (means Southern Barbarian). However, the specific situation of the treatment of Nanman titles by various dynasties has not been explored. In addition, the Nanman never stopped paying tribute to the Central Dynasty. No one is involved in whether tribute can earn the respect that the dynasty deserves. Nowadays, big data technology can easily handle massive amounts of literature, and it is entirely possible to analyze the above issues from "official histories" (the 25 historical books) using the method of word frequency research. The words frequency shows that since the unification of Lingnan by Emperor Qin Shi Huang, the feudal dynasties presented a paradox to Lingnan: The products in Lingnan were coveted, and local customs were despised. "Tribute" was used to cover up the predatory nature of Kings, and "Nanman" was used to establish political, national and cultural rank. The number of "tribute" and the meaning of "Nanman" formed the "magic mirror" development relationship in the big tree of feudal autocracy until the end of the Qing Dynasty. But on the one hand, the positive factors of "tribute" were absorbed and used by the western powers to establish their own alliances. On the other hand, they also mislead the public opinion and create trouble. Although "Nanman" has been eradicated politically, the regional discrimination and cultural misreading it contains have not been eradicated and often occurs. "Tribute" ranges from Kyushu to overseas to international relations. The connotation of "Nanman" from the orientation, nation and culture, the meaning of these two words has been spontaneously changing. It is timely to clarify their relationship and help make China revive.

The effect of board of directors’ characteristics on disclosing tone in the annual reports: evidence from Amman stock exchange

PurposeThis study examines the impact of board characteristics (i.e., board independence, board size, number of board meetings, foreign directors, and representation of females on the board of directors) on the tone disclosed in the banks’ annual reports of the Jordanian banking industry.Design/methodology/approachThe sample of this study contains all banks in the Jordanian banking industry for the period 2010–2019. This study employs a quantitative research method to examine the impact of the board of directors' characteristics on the tone of disclosure. Although disclosure tone is qualitative information, it has been converted into numbers (the frequency of positive and negative words) using the NVivo program. The "tone" is measured in this study based on lists of positive and negative words developed by Loughran and McDonald’s list. Then, a pooled regression analysis is used to investigate whether the board of directors' characteristics affect the disclosure tone.FindingsThe study results show that corporate governance plays a significant role in disclosing tone in banks’ annual reports. Clearly, the results show that the number of board meetings positively impacts the emergence of tone disclosure. In addition, the presence of women on the board of directors positively impacts the tone disclosure. In contrast, the foreign directors’ existence on the board of directors has a negative effect on the tone disclosure. However, the results show no relationship between board independence, size, and tone disclosure.Originality/valueThis study contributes by providing knowledge and insights into tone disclosure in an emerging market. Based on signaling theory, tone disclosures are the mangers’ signals given to the stakeholders in their firms’ financial reports. Managers disclosing positive tones to convey good news to their stockholders, and this considered as one of the main targets for these managers. This study provides insights into the relatively under-researched area of disclosure tone in an emerging market. It sheds light critically on how board of directors’ characteristics within the banking industry in Jordan contributes to their disclosure tone in the annual reports. This contribution helps stakeholders including policymakers, CEOs, and capital market participants understand how board members’ characteristics can contribute in building a straightforward disclosure tone in their financial reports. The study's conclusions are particularly significant because they attest to the need for financial knowledge and diversity of gender. The tone disclosure presented in financial reports, along with its anticipated impact on future investor decisions, is a crucial aspect for stakeholders to comprehend.Practical implicationsOur findings suggest that banks in Jordan should carefully consider the characteristics of their boards of directors, as these are crucial to ensuring transparency in disclosures. Additionally, maintaining a consistent and clear tone in annual reports is vital, as it significantly influences investor confidence and interest. This transparency can be strengthened by the quality and effectiveness of the bank's directors.Recommendations/future researchFor future research, the current study results can be reinvestigated to other emerging countries, other sectors, other measures for the disclosure tone and the board of directors’ characteristics, and more important different periods to include the effects of COVID-19 pandemic and financial crisis.

Ethical Concerns Upon Artificial Intelligence Empowered Human Resource Management: A Qualitative Study among Middle-level Managers from Beijing Technology Companies

The evolution of artificial intelligence (AI) in organizational management has significantly enhanced operational efficiency. However, it has introduced ethical challenges in human resource management. Between January to March 2024, this study conducted 21 semi-structured interviews with middle-level managers from high-tech companies in Beijing. Through word frequency analysis, the study found that key topics among the managers were “company,” “data,” “system,” and “problem,” with “AI” frequently recurring in the discussions. Sentiment analysis revealed generally favorable attitudes toward AI in human resource management (AI-HRM), along with nuanced emotional expressions such as inquiry, introspection, recommendation, challenge, adaptation, resistance, and indifference. The sentiment distribution of keywords aligned with topic trends. Thematic analysis identified key ethical concerns in AI-HRM, including issues related to data collection and utilization, human versus machine decision-making, quantitative versus qualitative assessment methodologies, the balance between fairness and efficiency, the need for trustworthy, explainable, and transparent AI, and the oversight of AI-HRM. This study contributes to the ethical investigation of AI-HRM from the perspective of middle-level managers, highlighting themes that are critical for understanding the theory, application, and future development of AI-HRM.

Этнокультурные особенности в представлениях о семье как ресурсе жизнеспособности у русской и бурятской молодежи

<p style="text-align: justify;"><strong>Objective.</strong> Comparative analysis of representations about family as a resilience resource among Russian and Buryat youth (15 to 24 years old).<br><strong>Background.</strong> The influence of family on human resilience is mediated by cultural and ethnic contexts. A comparative analysis of the concepts of family as a resource of youth resilience, due to the families belonging to different cultures – more collectivist (Buryats) and more individualistic (Russians), will help to clarify the ethnocultural features of human resilience. <br><strong>Study </strong><strong>d</strong><strong>esign.</strong> A comparison was made of the concepts of family as a resource of resilience among Russian and Buryat respondents who support their resilience. <br><strong>Participants.</strong> 109 Russian and 98 Buryat university and college students. A total of 207 people. <br><strong>Measurements.</strong> The following were used: focus groups, a socio-demographic questionnaire, the Twenty Statements Test by M. Kuhn and T. McPartland, and the author's version of the "Unfinished Sentences" method. Based on the qualitative data from focus groups on the essence of human resilience and its components, 9 unfinished sentences were formulated and combined into 4 categories: "Resilience", "Family", "Values", and "Culture". For quantitative formalization of the qualitative data of respondents, the lexical base (<em>n</em> = 3921 for Buryats, <em>n</em> = 4124 for Russians) was processed using the Atlas.ti program (version 9.5.6) and subjected to comparative lexicographic content analysis with an assessment of word frequency. The results are visualized as word clouds. <br><strong>Results</strong>. The semantic core in the "Resilience" category is different: himself, ability for Russians; person, ability for Buryats. In the core of the "Family" category – person, child – for Russians; good, beloved – for Buryats. Respondents of both groups report the high importance of family. For Russians, family members are equal, there are negative characteristics of family, while for Buryats, family relationships are usually hierarchical, there are no negative characteristics. In the core of the "Values" category for Russians: family, life; family, friends – for Buryats. In the core of the "Culture" category: the word many, tradition for Russians; important, tradition for Buryats. Interest in folk traditions was revealed in both samples. For Russians, traditions are associated with family, for Buryats with the traditions of the nation. The statements show the opposition of "I" (for Russians) and "we" (for Buryats). <br><strong>Conclusion</strong>. The ideas about family as a resource of resilience among Russian and Buryat youth have ethnocultural features. They are determined by the fact that the Buryats belong to a more collectivist culture and the Russians to a more individualistic culture. Russian youth perceive family as a resource of resilience, which is aimed at: strengthening their ability to cope with difficulties independently and forming an "I" identity. For Buryat youth, family as a resource of resilience strengthens their “we” identity, which contributes to the development of “We” identity. The idea of the ethnocultural context of the family as a resource of youth resilience allow us to understand how the family support for the younger generation varies.</p>

A Structural Topic and Sentiment-Discourse Model for Text Analysis

We consider the common setting where one observes a large number of opinionated text documents and related covariates, such as the text of online reviews along with the date of the review and the author demographic information. In this setting it can be of interest to understand how the covariates determine the text composition, as well as the prevalence, sentiment, and/or discourse of various discussion themes. Yet, most topic modeling methods in the machine learning literature are designed to summarize the text for the purpose of exploratory analysis and not to perform this type of formal statistical inference. Further, topic modeling methods generally do not try to estimate the sentiment or discourse of discussion along separate topics that can be critical in business applications (e.g., for summarizing service or product quality). We develop a topic model called the structural topic and sentiment-discourse (STS) model that introduces a new document-level latent variable that captures the sentiment and/or discourse (termed as “sentiment-discourse”) for each topic, which modulates the word frequency within a topic. These latent topic sentiment-discourse variables are controlled by document-level covariates to allow for experimental control and regression analysis. We also introduce new computational methods to resolve scalability issues that have forced previous models to restrict to a small number of categorical covariates. We benchmark the STS model on three real-world data sets from surveys, blogs, and Yelp restaurant reviews around the COVID-19 pandemic. Our model recovers meaningful results including rich insights about how COVID-19 affects online reviews, demonstrating that the STS model can be useful for regression analysis with text data in addition to topic modeling’s traditional use of descriptive analysis. This paper was accepted by Anindya Ghose, information systems. Supplemental Material: The online appendices and data files are available at https://doi.org/10.1287/mnsc.2022.00261 . An updated version of the R package implementing the STS model is available at https://CRAN.R-project.org/package=sts .

A text sentiment analysis method based on BiGRU and capsule network

Most of the existing sentiment analysis methods based on product review texts rarely consider the aspect features of the review texts, and the relevant analysis models do not consider the long-term contextual dependency features and local text features at the same time, thus affecting the accuracy of sentiment analysis. A text sentiment analysis method based on a bidirectional gated recurrent network (BiGRU) and a capsule network is proposed. This method first uses a word frequency statistics-based method to extract the aspect features of the review text and integrates them into the word vector representation, thereby effectively improving the expressive power of the word vector. Then, BiGRU is used to extract the long-term contextual dependency features of the text, and the capsule network is used to extract the local features of the text, thereby achieving high-precision text sentiment analysis based on aspects. Experimental results on real datasets show that the proposed method is superior to existing sentiment analysis models such as bidirectional long short-term memory network (BiLSTM), CNN-LSTM, and TextCNN in terms of evaluation indicators such as accuracy, precision, recall, and score.

Lexical Analysis of Japanese Children’s Songs from the Perspective of Japanese Language Education

Japanese children's songs can be a valuable resource for adult learners of the language, Firstly, the vocabulary used in children's songs is predominantly high-frequency and foundational, with a large portion falling below the N2 proficiency level. By mastering the words and phrases found in these songs, learners can expand their conversational abilities beyond the confines of traditional textbooks. Secondly, the songs offer a balanced representation of positive, negative, and neutral emotions, reflecting the emotional range and nuances of the Japanese language. This exposure to diverse emotional expressions can enrich learners' understanding of language and cultural nuances. Moreover, the study's semantic analysis reveals frequent word associations and co-occurrences, which can help learners grasp the interconnectedness of Japanese vocabulary and the cultural contexts in which words are used. Importantly, children's songs are deeply rooted in Japanese culture, indirectly exposing learners to various cultural aspects, such as the appreciation of nature, the concept of transience, and the importance of harmony and interconnectedness. This cultural immersion can foster a deeper understanding and appreciation of Japanese values and traditions. Furthermore, the familiar melodies and sing-along nature of these songs can facilitate social bonding and interpersonal connections among learners and native speakers. Engaging in shared cultural experiences, such as singing nursery rhymes together, can create a sense of community and strengthen the bond between learners and the target language culture.