Computational Linguistic Analysis Research Articles

Mixed methods research on reflective writing in teacher education.

In this paper, mixed methods research is presented and discussed in the context of research on reflective writing for the professional development of pre-service teachers. First, we present prominent theoretical frameworks to analyze reflective writings. Second, we review relevant methodological approaches of research on reflective writings in teacher education, such as qualitative, quantitative and mixed methods. Third, we present a study from our research lab combining qualitative content analysis and linguistic analyses as an example for a concurrent mixed method approach. The results of the qualitative content analysis indicated that 198 reflective writings of pre-service teachers were primarily descriptive and on a low level. Computational linguistic analyses revealed that affective and cognitive terminology utilization in reflective writing differed significantly across the different levels of reflection, with a higher frequency of such terms correlating with deeper levels of reflection. Thus, essential challenges and opportunities of implementing such a mixed method study to analyze reflective writings are illustrated and discussed. Finally, we conclude the paper by discussing on how mixed methods approaches might be further advanced in the field of reflective writing research in teacher education.

EP.06A.01 Computational Linguistic Analysis for the Isolation of Propitious miRNA Biomarkers in Lung Cancer

EP.06A.01 Computational Linguistic Analysis for the Isolation of Propitious miRNA Biomarkers in Lung Cancer

Unveiling Entrepreneurship in Chinese State-Owned Enterprises: A Computational Linguistic Analysis

Unveiling Entrepreneurship in Chinese State-Owned Enterprises: A Computational Linguistic Analysis

Lexical Construction of Character Names in the Collection of Short Stories "Robohnya Surau Kami" By A.A. Navis

This research aims to analyze the lexical construction in the short story collection "Robohnya Surau Kami" by A.A. Navis. The lexical construction that is focused on is the lexical construction of the characters in the short story collection. This research uses a descriptive qualitative approach and a corpus linguistics approach. The corpus linguistic application used in this research is the KORTARA application (Korpus Nusantara). The data collection technique used in this research is documentation techniques, which are sourced from the corpus. The documentation technique used in this research comes from the corpus files contained in the corpus linguistic application (Korpus Nusantara). The corpus target of this research is a short stories corpus. This research uses computational linguistic analysis techniques. The computational linguistic technique in this research goes through several stages, namely identification, classification, interpretation and conclusion Based on the research that has been carried out, several types of character construction have been obtained, namely (1) gender terms, (2) kinship terms in Indonesian, (3) kinship terms in Minangkabau, (4) personal names, (5) country names, (6) common nouns , (7) creator/creator, (8) formal profession/position title, (9) non-formal profession/position title, and (10) pronoun.

Characterizing Features of Creative Writing in Older Adults.

How does creative expression change across the life span? Although creativity is generally preserved well into adulthood, certain cognitive functions, such as episodic detail and ideational fluency, have been shown to decline with age. The present study employs computational linguistic analyses to investigate the salient features of creative writing in older adults. We collected short stories from a sample of 50 older adults (age 65≤) which were subsequently rated for creativity by an independent set of participants. Mixed-effects linear regression models were used to describe semantic diversity and perceptual details as predictors of creativity. Semantic diversity reflects the extent to which a narrative connects divergent ideas and is closely associated with creativity. Perceptual details, characterized by sensorial descriptions, have been previously associated with creative writing and may serve to transport readers to alternative times and places. Additionally, we compare these measures to a previously collected sample of stories from younger adults. Results indicate that the presence of perceptual details and semantic diversity were significant positive predictors of creativity (p < .05). Moreover, we find that stories written by older adults contain fewer perceptual details compared with stories written by younger adults. These results advance our understanding of age-related changes in creativity and highlight the potential role of episodic simulation in writing creative short stories.

Investigating Health and Well-Being Challenges Faced by an Aging Workforce in the Construction and Nursing Industries: Computational Linguistic Analysis of Twitter Data.

Construction and nursing are critical industries. Although both careers involve physically and mentally demanding work, the risks to workers during the COVID-19 pandemic are not well understood. Nurses (both younger and older) are more likely to experience the ill effects of burnout and stress than construction workers, likely due to accelerated work demands and increased pressure on nurses during the COVID-19 pandemic. In this study, we analyzed a large social media data set using advanced natural language processing techniques to explore indicators of the mental status of workers across both industries before and during the COVID-19 pandemic. This social media analysis aims to fill a knowledge gap by comparing the tweets of younger and older construction workers and nurses to obtain insights into any potential risks to their mental health due to work health and safety issues. We analyzed 1,505,638 tweets published on Twitter (subsequently rebranded as X) by younger and older (aged <45 vs >45 years) construction workers and nurses. The study period spanned 54 months, from January 2018 to June 2022, which equates to approximately 27 months before and 27 months after the World Health Organization declared COVID-19 a global pandemic on March 11, 2020. The tweets were analyzed using big data analytics and computational linguistic analyses. Text analyses revealed that nurses made greater use of hashtags and keywords (both monograms and bigrams) associated with burnout, health issues, and mental health compared to construction workers. The COVID-19 pandemic had a pronounced effect on nurses' tweets, and this was especially noticeable in younger nurses. Tweets about health and well-being contained more first-person singular pronouns and affect words, and health-related tweets contained more affect words. Sentiment analyses revealed that, overall, nurses had a higher proportion of positive sentiment in their tweets than construction workers. However, this changed markedly during the COVID-19 pandemic. Since early 2020, sentiment switched, and negative sentiment dominated the tweets of nurses. No such crossover was observed in the tweets of construction workers. The social media analysis revealed that younger nurses had language use patterns consistent with someone experiencing the ill effects of burnout and stress. Older construction workers had more negative sentiments than younger workers, who were more focused on communicating about social and recreational activities rather than work matters. More broadly, these findings demonstrate the utility of large data sets enabled by social media to understand the well-being of target populations, especially during times of rapid societal change.

Towards AI-Driven Healthcare: Systematic Optimization, Linguistic Analysis, and Clinicians' Evaluation of Large Language Models for Smoking Cessation Interventions.

Creating intervention messages for smoking cessation is a labor-intensive process. Advances in Large Language Models (LLMs) offer a promising alternative for automated message generation. Two critical questions remain: 1) How to optimize LLMs to mimic human expert writing, and 2) Do LLM-generated messages meet clinical standards? We systematically examined the message generation and evaluation processes through three studies investigating prompt engineering (Study 1), decoding optimization (Study 2), and expert review (Study 3). We employed computational linguistic analysis in LLM assessment and established a comprehensive evaluation framework, incorporating automated metrics, linguistic attributes, and expert evaluations. Certified tobacco treatment specialists assessed the quality, accuracy, credibility, and persuasiveness of LLM-generated messages, using expert-written messages as the benchmark. Results indicate that larger LLMs, including ChatGPT, OPT-13B, and OPT-30B, can effectively emulate expert writing to generate well-written, accurate, and persuasive messages, thereby demonstrating the capability of LLMs in augmenting clinical practices of smoking cessation interventions.

Food (di)lemmas: disentangling the Italian Local Food Policy narratives

Recently, food-related policy initiatives have proliferated, such as food strategies, food plans, food councils, food districts and food communities, just to name the more relevant ones. Far from being systematically defined and logically systematized, these concepts often overlap or are used as synonyms. The paper has systematically traced the current trends showing how these concepts are used in the current debate, the theoretical background on which they are grounded and the public policies they call for, following a threefold approach: (1) a literature analysis to establish the state of academic research on food systems in its multidimensionality; (2) a review of the existing national legislation to detect the utilization of food policy-related lemmas in the normative; (3) a computational linguistic analysis applied on institutional documentation to explore how cities and territories are using concepts and definitions in the grey literature. The results show that the construction of narratives around the topic of food systems planning is experiencing a momentum, with particular emphasis on principles, background premises and governance aspects. In this context, the risk of marginality for the agricultural sector in such discourses and narratives is highlighted.

Creative Evaluation: The Role of Memory in Novelty & Effectiveness Judgements

ABSTRACT How do we assess the quality of an idea? Current theories suggest that episodic memory contributes to creative ideation, implicating memory retrieval and mental simulation in the generation of creative ideas; however, the role of memory in creative evaluation has not been systematically examined. Across two independent online samples (Study 1 n = 50, Study 2 n = 626), we explore how episodic retrieval supports the evaluation of two distinct aspects of creativity: novelty and effectiveness. In both studies, participants were presented with a series of creative ideas – responses on the alternate uses task – and were asked to independently rate them for novelty/effectiveness. Following each rating, participants were prompted to reflect on their process and type a brief description about how they made their evaluation. We apply computational linguistic analysis to quantify the prevalence of episodic/perceptual details (sights, sounds, etc.) in each evaluation, along with past-focused and future-focused words. Consistent with prior work, we observe a negative correlation (r=-.39) between novelty and effectiveness ratings. Ordinal logistic regression models indicate that perceptual detail and temporal orientation of evaluations are predictive of novelty and effectiveness ratings. We show that people refer more to the past when evaluating familiar, effective ideas; conversely, people refer more to the future when evaluating highly novel, less effective ideas. Overall, these results are consistent with the hypothesis that episodic retrieval supports the evaluation of creative ideas.

A computational linguistic analysis of the anatomy of production, consumption, and diffusion of misinformation and authentic information in social media: The case of the COVID-19 pandemic

Social media has become a powerful conduit for misinformation during major public events. As a result, an extant body of research has emerged on misinformation and its diffusion. However, the research is fragmented and has mainly focused on understanding the content of misinformation messages. Little attention is paid to the production and consumption of misinformation. This study presents the results of a detailed comparative analysis of the production, consumption, and diffusion of misinformation with authentic information. Our findings, based on extensive use of computational linguistic analyses of COVID-19 pandemic-related messages on the Twitter platform, revealed that misinformation and authentic information exhibit very different characteristics in terms of their contents, production, diffusion, and their ultimate consumption. To support our study, we carefully selected a sample of 500 widely propagated messages confirmed by fact-checking websites as misinformation or authentic information about pandemic-related topics from the Twitter platform. Detailed computational linguistic analyses were performed on these messages and their replies ( N = 198,750). Additionally, we analyzed approximately 1.2 million Twitter user accounts responsible for producing, forwarding, or replying to these messages. Our extensive and detailed findings were used to develop and propose a theoretical framework for understanding the diffusion of misinformation on social media. Our study offers insights for social media platforms, researchers, policymakers, and online information consumers about how misinformation spreads over social media platforms.

Evaluating Reflective Writing in Pre-Service Teachers: The Potential of a Mixed-Methods Approach

Reflective writing is a relevant aspect of pre-service teachers’ professionalization. Evaluating reflective writing in teacher education is demanding due to a shortage of resources. Hence, this study explores the practical possibilities of evaluating reflective writing using a mixed-methods approach to analyze reflective writing from 198 pre-service teachers at a German university. We used qualitative content analysis, computational linguistic approaches, and BERTopic. Results of qualitative content analysis results indicated primarily descriptive and low-level participants’ reflective writing. Next, computational linguistic analyses revealed that affective and cognitive terminology utilization differed across varying levels of reflection, with a higher frequency of such terms correlating with deeper levels of reflection. BERTopic results showed that reflective content mainly centered on learning materials and shifted toward affective and motivational themes related to higher levels of reflection. This study demonstrates that reflective writing can be evaluated across reflection levels and cognitive, affective, and thematic dimensions, combining qualitative content analysis, computational linguistic approaches, and BERTopic.

A longitudinal investigation of pragmatic language across contexts in autism and related neurodevelopmental conditions.

Pragmatic language, or the use of language in social contexts, is a critical skill in daily life, supporting social interactions and the development of meaningful social relationships. Pragmatic language is universally impacted in autism spectrum disorder (ASD) and pragmatic deficits are also common in other neurodevelopmental conditions, particularly those related to ASD, such as fragile X syndrome (FXS). This study used a multi-method, longitudinal approach to characterize potentially unique pragmatic profiles across different neurodevelopmental disabilities, and across contexts that varied in degree of social demand. The utility of computational linguistic analyses, as an efficient tool for capturing pragmatic abilities, was also explored. Pragmatic skills of boys with idiopathic ASD (ASD-O, n = 43), FXS with and without ASD (FXS-ASD, n = 57; FXS-O, n = 14), Down syndrome (DS, n = 22), and typical development (TD, n = 24) were compared using variables obtained from a standardized measure, narrative, and semi-naturalistic conversation at up to three time points. Pragmatic language was most significantly impacted among males with ASD-O and FXS-ASD across all three contexts, with more difficulties in the least structured context (conversation), and also some differences based on FXS comorbidity. Patterns of group differences were more nuanced for boys with FXS-O and DS, with context having less of an impact. Clinical groups demonstrated minimal changes in pragmatic skills with age, with some exceptions. Computational language measurement tools showed some utility for measuring pragmatic skills, but were not as successful as traditional methods at capturing differences between clinical groups. Overlap and differences between ASD and other forms of neurodevelopmental disability in general, and between idiopathic and syndromic ASD in particular, have important implications for developing precisely tailored assessment and intervention approaches, consistent with a personalized medicine approach to clinical study and care in ASD.

Various Word Shorts in the Podcast of Political Figures Sandiaga Uno: Corpus-Based Analysis

This study aims to examine the use of abbreviation in the political figure Sandiaga Uno's podcast. This research will also bring up the use of corpus linguistics which is very effective in research in the field of linguistics, especially abbreviation or shortening of words. This type of research is a descriptive qualitative research. The advanced method which is the main approach of this research is the corpus linguistic method. Corpus linguistics can be interpreted as research that relies on linguistic data analysis using digital technology. The data in this study were collected using documentation techniques and utilizing the KORTARA (Korpus Nusantara) application which originates from the Wawancara Tokoh Indonesia corpus. Research data in this study will be analyzed using the KORTARA application. Analysis using the KORTARA application can be referred to as computational linguistics, because it utilizes corpus linguistics applications. The work steps of this computational linguistic analysis start from identifying data, classifying data, interpreting data, and drawing conclusions. The findings of this study reveal that the use of abbreviations in the video podcast of political figure Sandiaga Uno can be in the form of abbreviations, acronyms, and fragments. This research reveals that the most dominant type of abbreviation used in the podcast is fragment. The results of the data analysis also revealed that there were no types of abbreviations for letter symbols and contractions, this was based on the theme or discussion in the video which was not too focused on economic issues, but politics. The findings of abbreviation data in this study also reveal that the use of abbreviated or abbreviated language will continue to be used by political figures, in order to build better and more familiar communication with their interlocutors.

A Multimodal Emotion Perspective on Social Media Influencer Marketing: The Effectiveness of Influencer Emotions, Network Size, and Branding on Consumer Brand Engagement Using Facial Expression and Linguistic Analysis

Social media influencers rely on emotional connection to maintain and grow their followings and have value for brands. To date, however, no research has quantitatively examined the impact of emotion in the facial expressions and caption text that influencers use in their video posts on consumer engagement through likes, comments, and views of posts. Grounded in consumer brand engagement, psychological sense of community, and the behavior ecology view of facial displays, this study uses social media analytics, facial expression analysis, and computational linguistic analysis to assess the emotional substance of 402 video posts by prominent micro-, macro-, and mega-influencer mothers, known as InstaMoms, as exemplars of Instagram influencers. The study identifies that the amount of emotion used and specific discrete emotions have a meaningful influence on engagement, and both follower count and presence of branding saliently contribute to a more robust understanding of the relationship. Theoretical and practical implications are identified and discussed.

Cognitive and social well-being in older adulthood: The CoSoWELL corpus of written life stories.

This paper presents the Cognitive and Social WELL-being (CoSoWELL) project that consists of two components. One is a large corpus of narratives written by over 1000 North American older adults (55+ years old) in five test sessions before and during the first year of the COVID-19 pandemic. The other component is a rich collection of socio-demographic data collected through a survey from the same participants. This paper introduces the first release of the corpus consisting of 1.3 million tokens and the survey data (CoSoWELL version 1.0). It also presents a series of analyses validating design decisions for creating the corpus of narratives written about personal life events that took place in the distant past, recent past (yesterday) and future, along with control narratives. We report results of computational topic modeling and linguistic analyses of the narratives in the corpus, which track the time-locked impact of the COVID-19 pandemic on the content of autobiographical memories before and during the COVID-19 pandemic. The main findings demonstrate a high validity of our analytical approach to unique narrative data and point to both the locus of topical shifts (narratives about recent past and future) and their detailed timeline. We make the CoSoWELL corpus and survey data available to researchers and discuss implications of our findings in the framework of research on aging and autobiographical memories under stress.Supplementary InformationThe online version contains supplementary material available at 10.3758/s13428-022-01926-0.

Firm-level political risk, liquidity management, and managerial attributes

This study examines how firm-level political risk (FLPR) relates to excess cash holding and cash value. Managerial ability and psychological confidence are examined as moderators of these relationships. FLPR is measured by a computational linguistic analysis of firm conference call manuscripts. The findings indicate that FLPR has a positive (negative) relationship to excess cash (cash value) and that the managerial ability and CEO overconfidence of managers have a negative (positive) moderating effect on excess cash holdings (cash value). Robustness tests show consistent results using national-level policy uncertainty and alternative empirical models.

Understanding the Message and Formulation of Fake Online Reviews: A Language-production Model Perspective

Consumers have become ever more reliant on online reviews. Therefore, fake reviews have also become increasingly rampant and eroded online review platforms’ credibility. Previous literature suggests that particular linguistic styles can manifest in fake reviews with reference to the varying stages of the language-production process. Drawing on the language-production model as our theoretical foundation, we examine the psycholinguistic styles of fake online reviews at the message and formulation level. We performed a computational linguistic analysis on 66,940 reviews from Yelp. Our results suggest that fake reviews align more with deceptive writing in terms of the message-level variables such as length and psychological (affective, cognitive, social, and perceptual) cues. Interestingly, we found that they align less with deceptive writing in terms of the formulation-level variables such as readability, pronouns, and part-of-speech tags, which may be due to the fake review writers’ conscious attempt to follow the language styles that genuine reviews adopt.

NLQ into SQL translation using computational linguistics

This research discusses the implementation experiment of an automatic translation of an unstructured Natural Language Question (NLQ) into a Structured Query Language (SQL) statement. SQL is used as a Relational DataBase (RDB) interaction language with special query syntax and a computer- executable artificial language. This way, DataBase (DB) administrators or general users with little or no SQL querying abilities can perform queries on RDBs in an interactive manner. The main goal of this work is to exploit a manually written rule- based mapping constraints algorithm. This algorithm maps NLQ tokens’ semantic/syntactic information into RDB elements’ semantic roles (i.e., value, attribute) via pairing and matching means. The matching RDB elements, called “identified lexica”, are then mapped into the SQL clauses consistently for SQL generation and execution. The matching process uses a computational linguistic analysis mapping algorithm, represented in the MetaTables. This mapping algorithm proved to be efficient especially with small RDBs with an accuracy of 95% and is about 93% accurate with larger RDBS.

Computational Linguistic Analysis of the Constancy of Mathematics Education in Japanʼs Course of Study

Computational Linguistic Analysis of the Constancy of Mathematics Education in Japanʼs Course of Study

Multivariate computational linguistic analysis for early detection of cognitive impairment

AbstractBackgroundThe overarching goal of this study was to develop a novel computational linguistic algorithm that can be used to build a machine learning platform for recognizing changes in cognitive abilities during the progression of psychopathological disorders or predicting clinical prognosis following a brain injury or therapeutic interventions.MethodThe computational linguistic algorithm developed in this study evaluates lexical diversity, lexical complexity, and emotional tones in a quantitative manner. An existing algorithm that quantifies idea density was also included in this study. The initial proof‐of‐concept study was performed on various published books by well‐known authors, including Iris Murdoch who developed Alzheimer’s disease (AD) later in life. Ten interviews of patients with mild AD and ten interviews of healthy age‐matched individuals were evaluated. The transcript of each video was produced manually. Each transcript was analyzed using the computational linguistic algorithm for lexical diversity/complexity, emotional tones, and idea density. Quantitative linguistic values were compared between patients with mild AD and healthy age‐matched individuals.ResultA computational linguistic analysis of various books resulted in findings that were consistent with the nature and subject of each book. Among all the computational linguistic variables evaluated in this study, the book written by Irish Murdoch after the onset of AD showed a decrease in the level of lexical complexity by 17.5%. Interestingly, a 20% decrease in the level of lexical complexity was also noted when video interviews of patients with mild AD were compared to normal age‐matched individuals. The video transcripts of AD patients showed a statistically significant increase in the levels of anger, fear, and sadness. We are currently conducting a study to compare computational linguistic variables in response to writing prompts between patients with mild AD and healthy age‐matched individuals. Preliminary results indicate that patients with AD show a similar decrease in the level of lexical complexity as well as quantifiable changes in emotional tones.ConclusionThe computational linguistic algorithm developed in this study may lead to a machine learning approach or artificial intelligence platform to detect linguistic changes that may occur in the human cognitive state for both diagnosis and/or prognosis of mental health conditions.