Data Technologies and Applications

vLex
Publisher:
Emerald Group Publishing Limited
Publication date:
2021-02-01
ISBN:
2514-9288

Issue Number

Latest documents

  • Optimized discovery of discourse topics in social media: science communication about COVID-19 in Brazil

    Purpose: Social media platforms that disseminate scientific information to the public during the COVID-19 pandemic highlighted the importance of the topic of scientific communication. Content creators in the field, as well as researchers who study the impact of scientific information online, are interested in how people react to these information resources and how they judge them. This study aims to devise a framework for extracting large social media datasets and find specific feedback to content delivery, enabling scientific content creators to gain insights into how the public perceives scientific information. Design/methodology/approach: To collect public reactions to scientific information, the study focused on Twitter users who are doctors, researchers, science communicators or representatives of research institutes, and processed their replies for two years from the start of the pandemic. The study aimed in developing a solution powered by topic modeling enhanced by manual validation and other machine learning techniques, such as word embeddings, that is capable of filtering massive social media datasets in search of documents related to reactions to scientific communication. The architecture developed in this paper can be replicated for finding any documents related to niche topics in social media data. As a final step of our framework, we also fine-tuned a large language model to be able to perform the classification task with even more accuracy, forgoing the need of more human validation after the first step. Findings: We provided a framework capable of receiving a large document dataset, and, with the help of with a small degree of human validation at different stages, is able to filter out documents within the corpus that are relevant to a very underrepresented niche theme inside the database, with much higher precision than traditional state-of-the-art machine learning algorithms. Performance was improved even further by the fine-tuning of a large language model based on BERT, which would allow for the use of such model to classify even larger unseen datasets in search of reactions to scientific communication without the need for further manual validation or topic modeling. Research limitations/implications: The challenges of scientific communication are even higher with the rampant increase of misinformation in social media, and the difficulty of competing in a saturated attention economy of the social media landscape. Our study aimed at creating a solution that could be used by scientific content creators to better locate and understand constructive feedback toward their content and how it is received, which can be hidden as a minor subject between hundreds of thousands of comments. By leveraging an ensemble of techniques ranging from heuristics to state-of-the-art machine learning algorithms, we created a framework that is able to detect texts related to very niche subjects in very large datasets, with just a small amount of examples of texts related to the subject being given as input. Practical implications: With this tool, scientific content creators can sift through their social media following and quickly understand how to adapt their content to their current user’s needs and standards of content consumption. Originality/value: This study aimed to find reactions to scientific communication in social media. We applied three methods with human intervention and compared their performance. This study shows for the first time, the topics of interest which were discussed in Brazil during the COVID-19 pandemic.

  • Understanding customer behavior by mapping complaints to personality based on social media textual data

    Purpose: Technology serves as a key catalyst in shaping society and the economy, significantly altering customer dynamics. Through a deep understanding of these evolving behaviors, a service can be tailored to address each customer's unique needs and personality. We introduce a strategy to integrate customer complaints with their personality traits, enabling responses that resonate with the customer’s unique personality. Design/methodology/approach: We propose a strategy to incorporate customer complaints with their personality traits, enabling responses that reflect the customer’s unique personality. Our approach is twofold: firstly, we employ the customer complaints ontology (CCOntology) framework enforced with multi-class classification based on a machine learning algorithm, to classify complaints. Secondly, we leverage the personality measurement platform (PMP), powered by the big five personality model to predict customer’s personalities. We develop the framework for the Indonesian language by extracting tweets containing customer complaints directed towards Indonesia's three biggest e-commerce services. Findings: By mapping customer complaints and their personality type, we can identify specific personality traits associated with customer dissatisfaction. Thus, personalizing how we offer the solution based on specific characteristics. Originality/value: The research enriches the state-of-the-art personalizing service research based on captured customer behavior. Thus, our research fills the research gap in considering customer personalities. We provide comprehensive insights by aligning customer feedback with corresponding personality traits extracted from social media data. The result is a highly customized response mechanism attuned to individual customer preferences and requirements.

  • A systematic review of the use of FHIR to support clinical research, public health and medical education

    Purpose: This systematic review aimed to identify and categorize applications using Fast Healthcare Interoperability Resources (FHIR) to support activities outside of direct healthcare provision. Design/methodology/approach: A systematic electronic search was performed, and 53 studies were included after the selection process. Findings: The results show that FHIR is being used to support (1) clinical research (i.e. clinical research based on interventional trials, data interoperability to support clinical research and advanced communication services to support clinical research), (2) public health and (3) medical education. Despite the FHIR potential to support activities outside of direct healthcare provision, some barriers were identified, namely difficulties translating the proposed applications to clinical environments or FHIR technical issues that require further developments. Originality/value: This study provided a broad review of how FHIR is being applied in clinical activities outside of direct clinical care and identified three major domains, that is, clinical research, public health and medical education, being the first and most representative in terms of number of publications.

  • Novel framework for learning performance prediction using pattern identification and deep learning

    Purpose: Educational data mining (EDM) discovers significant patterns from educational data and thus can help understand the relations between learners and their educational settings. However, most previous data mining techniques focus on prediction of learning performance of learners without integrating learning patterns identification techniques. Design/methodology/approach: This study proposes a new framework for identifying learning patterns and predicting learning performance. Two modules, the learning patterns identification module and the deep learning prediction models (DNN), are integrated into this framework to identify the difference of learning performance and predicting learning performance from profiles of students. Findings: Experimental results from survey data indicate that the proposed identifying learning patterns module could facilitate identifying valuable difference (change) patterns from student’s profiles. The proposed learning performance prediction module which adapts DNN also performs better than traditional machine techniques in prediction performance metrics. Originality/value: To our best knowledge, the framework is the only educational system in the literature for identifying learning patterns and predicting learning performance.

  • Assessing the alignment of corporate ESG disclosures with the UN sustainable development goals: a BERT-based text analysis

    Purpose: This study aims to provide measurable information that evaluates a company’s ESG performance based on the conceptual connection between ESG, non-financial elements of a company and the UN Sustainable Development Goals (SDGs) for resolving global issues. Design/methodology/approach: A novel data processing method based on the BERT is presented and applied to analyze the changes and characteristics of SDG-related ESG texts from companies’ disclosures over the past decade. Specifically, ESG-related sentences are extracted from 93,277 Form 10-K filings disclosed between 2010 and 2022 and the similarity between these extracted sentences and SDGs statements is calculated through sentence transformers. A classifier is created by fine-tuning FinBERT, a financial domain-specific pre-trained language model, to classify the sentences into eight ESG classes. Findings: The quantified results obtained from the classifier reveal several implications. First, it is observed that the trend of SDG-related ESG sentences shows a slow and steady increase over the past decade. Second, large-cap companies relatively have a greater amount of SDG-related ESG disclosures than small-cap companies. Third, significant events such as the COVID-19 pandemic greatly impact the changes in disclosure content. Originality/value: This study presents a novel approach to textual analysis using neural network-based language models such as BERT. The results of this study provide meaningful information and insights for investors in socially responsible investment and sustainable investment and suggest that corporations need a long-term plan regarding ESG disclosures.

  • A comparative analysis of job satisfaction prediction models using machine learning: a mixed-method approach

    Purpose: Because the food service industry is more dependent on customer contact and human resources than other industries, it is crucial to understand the factors influencing employee job satisfaction to ensure that employees provide satisfactory service to customers. However, few studies have incorporated employee reviews of job portals into their research. Many job seekers tend to trust company reviews posted by employees on job portals based on the information provided by the company itself. Thus, this study utilized company reviews and job satisfaction ratings from employees in the food service industry on a job portal site, Job Planet, to conduct mixed-method research. Design/methodology/approach: For qualitative research, we applied the Latent Dirichlet Allocation (LDA) model to food service industry company reviews to identify 10 job satisfaction factors considered important by employees. For quantitative research, four algorithms were used to predict job satisfaction ratings: regression tree, multilayer perceptron (MLP), random forest and XGBoost. Thus, we generated predictor variables for six cases using the probability values of topics and job satisfaction ratings on a five-point scale through LDA and used them to build prediction algorithms. Findings: The analysis showed that algorithm accuracy performed differently in each of the six cases, and overall, factors such as work-life balance and work environment have a significant impact on predicting job satisfaction ratings. Originality/value: This study is significant because its methodology and results suggest a new approach based on data analysis in the field of human resources, which can contribute to the operation and planning of corporate human resources management in the future.

  • A knowledge graph analysis tool of people and organizations to facilitate digital humanities research

    Purpose: To support digital humanities research more effectively and efficiently, this study develops a novel Knowledge Graph Analysis Tool of People and Organizations (KGAT-PO) for the Digital Humanities Research Platform for Biographies of Chinese Malaysian Personalities (DHRP-BCMP) based on artificial intelligence (AI) technology that would not only allow humanities scholars to look at the relationships between people but also has the potential for aiding digital humanities research by identifying latent relationships between people via relationships between people and organizations. Design/methodology/approach: To verify the effectiveness of KGAT-PO, a counterbalanced design was applied to compare research participants in two groups using DHRP-BCMP with and without KGAT-PO, respectively, to perform people relationship inquiry and to see if there were significant differences in the effectiveness and efficiency of exploring relationships between people, and the use of technology acceptance between the two groups. Interviews and Lag Sequential Analysis were also used to observe research participants’ perceptions and behaviors. Findings: The results show that the DHRP-BCMP with KGAT-PO could help research participants improve the effectiveness of exploring relationships between people, and the research participants showed high technology acceptance towards using DHRP-BCMP with KGAT-PO. Moreover, the research participants who used DHRP-BCMP with KGAT-PO could identify helpful textual patterns to explore people’s relationships more quickly than DHRP-BCMP without KGAT-PO. The interviews revealed that most research participants agreed that the KGAT-PO is a good starting point for exploring relationships between people and improves the effectiveness and efficiency of exploring people’s relationship networks. Research limitations/implications: The research’s limitations encompass challenges related to data quality, complex people relationships, and privacy and ethics concerns. Currently, the KGAT-PO is limited to recognizing eight types of person-to-person relationships, including couple, sibling, parent-child, friend, teacher-student, relative, work, and others. These factors should be carefully considered to ensure the tool’s accuracy, usability, and ethical application in enhancing digital humanities research. Practical implications: The study’s practical implications encompass enhanced research efficiency, aiding humanities scholars in uncovering latent interpersonal relationships within historical texts with high technology acceptance. Additionally, the tool’s applications can extend to social sciences, business and marketing, educational settings, and innovative research directions, ultimately contributing to data-driven insights in the field of digital humanities. Originality/value: The research’s originality lies in creating a Knowledge Graph Analysis Tool of People and Organizations (KGAT-PO) using AI, bridging the gap between digital humanities research and AI technology. Its value is evident in its potential to efficiently uncover hidden people relationships, aiding digital humanities scholars in gaining new insights and perspectives, ultimately enhancing the depth and effectiveness of their research.

  • Analysis of CEO career patterns using machine learning: taking US university graduates as an example

    Purpose: This study explores the career trajectories of Chief Executive Officers (CEOs) to uncover unique characteristics that contribute to their success. By utilizing web scraping and machine learning techniques, over two thousand CEO profiles from LinkedIn are analyzed to understand patterns in their career paths. This study offers an alternative approach compared to the predominantly qualitative research methods employed in previous research. Design/methodology/approach: This study proposes a framework for analyzing CEO career patterns. Job titles and company information are encoded using the Standard Occupational Classification (SOC) scheme. The study employs the Needleman-Wunsch optimal matching algorithm and an agglomerative approach to construct distance matrices and cluster CEO career paths. Findings: This study gathered data on the career transition processes of graduates from several renowned public and private universities in the United States via LinkedIn. Employing machine learning techniques, the analysis revealed diverse career trajectories. The findings offer career guidance for individuals from various academic backgrounds aspiring to become CEOs. Research limitations/implications: The building of a career sequence that takes into account the number of years requires integers. Numbers that are not integers have been rounded up to facilitate the optimal matching process but this approach prevents a perfectly accurate representation of time worked. Practical implications: This study makes an original contribution to the field of career pattern analysis by disclosing the distinct career path groups of CEOs using the rich LinkedIn online dataset. Note that our CEO profiles are not restricted in any industry or specific career paths followed to becoming CEOs. In light of the fact that individuals who hold CEO positions are usually perceived by society as successful, we are interested in finding the characteristics behind their success and whether either the title held or the company they remain at show patterns in making them who they are today. Originality/value: As a matter of fact, nearly all CEOs had previous experience working for a non-Fortune organization before joining a Fortune company. Of those who have worked for Fortune firms, the number of CEOs with experience in Fortune 500 forms exceeded those with experience in Fortune 1,000 firms.

  • MD-LDA: a supervised LDA topic model for identifying mechanism of disease in TCM

    Purpose: In traditional Chinese medicine (TCM), the mechanism of disease (MD) constitutes an essential element of syndrome differentiation and treatment, elucidating the mechanisms underlying the occurrence, progression, alterations and outcomes of diseases. However, there is a dearth of research in the field of intelligent diagnosis concerning the analysis of MD. Design/methodology/approach: In this paper, we propose a supervised Latent Dirichlet Allocation (LDA) topic model, termed MD-LDA, which elucidates the process of MDs identification. We leverage the label information inherent in the data as prior knowledge and incorporate it into the model’s training. Additionally, we devise two parallel parameter estimation algorithms for efficient training. Furthermore, we introduce a benchmark MD identification dataset, named TMD, for training MD-LDA. Finally, we validate the performance of MD-LDA through comprehensive experiments. Findings: The results show that MD-LDA is effective and efficient. Moreover, MD-LDA outperforms the state-of-the-art topic models on perplexity, Kullback–Leibler (KL) and classification performance. Originality/value: The proposed MD-LDA can be applied for the MD discovery and analysis of TCM clinical diagnosis, so as to improve the interpretability and reliability of intelligent diagnosis and treatment.

  • Early identification of high attention content for online mental health community users based on multi-level fusion model

    Purpose: The overload of user-generated content in online mental health community makes the focus and resonance tendencies of the participating groups less clear. Thus, the purpose of this paper is to build an early identification mechanism for users' high attention content to promote early intervention and effective dissemination of professional medical guidance. Design/methodology/approach: We decouple the identification mechanism from two processes: early feature combing and algorithmic model construction. Firstly, based on the differentiated needs and concerns of the participant groups, the multiple features of “information content + source users” are refined. Secondly, a multi-level fusion model is constructed for features processing. Specifically, Bidirectional Encoder Representation from Transformers (BERT)-Bi-directional Long-Short Term Memory (BiLSTM)-Linear are used to refine the semantic features, while Graph Attention Networks (GAT) is used to capture the entity attributes and relation features. Finally, the Convolutional Neural Network (CNN) is used to optimize the multi-level fusion features. Findings: The results show that the ACC of the multi-level fusion model is 84.42%, F1 is 79.43% and R is 76.71%. Compared with other baseline models and single feature elements, the ACC and F1 values are improved to different degrees. Originality/value: The originality of this paper lies in analyzing multiple features based on early stages and constructing a new multi-level fusion model for processing. Further, the study is valuable for the orientation of psychological patients' needs and early guidance of professional medical care.

Featured documents

Add as a preferred source on Google