Text Mining Model Research Articles

Analyzing User Reviews on Digital Detox Apps: A Text Mining and Sentiment Analysis Approach

ABSTRACTDue to the growing concerns around problematic smartphone use and its negative impact, there is a rising interest in digital detox. While many digital detox apps have been developed in recent years, there is still limited understanding of the long‐term effectiveness of digital detox applications and the attitude of people towards these apps. This study fills this gap by identifying the topics that people post in their reviews on the Google Play Store about digital detox apps and the emotion‐based sentiment of those reviews. A total of 3500 reviews of 25 digital detox apps were collected from the Google Play Store using a scraping tool called “Parsehub.” Data was analyzed using R studio. Sentiment analysis results suggest that positive sentiments dominated the data frame. “Trust” and “anticipation” were the two most expressed emotions in the reviews. Regression analysis confirmed that sentiment scores could explain the ratings of the apps. Through LDA topic modeling four major topics of the reviews were identified and are discussed in detail in the later section of the research paper. The findings of this study may help app developers and marketers improve digital detox apps so that people can learn and practice mindful smartphone use with the help of these apps. This study fills a gap in digital detox research by adopting a new methodological approach and procedure since it combines text mining, sentiment analysis (NRC Lexicon using Syuzhet package), regression analysis, and LDA topic modeling. To the best of our knowledge, this is the first study which uses this research approach in the context of digital detox apps.

Survey on Fake Review Detection System

Abstract: In today's business landscape, online reviews play a crucial role in shaping commerce. A large portion of purchase decisions for online products is driven by customer feedback. Consequently, some individuals or groups try to manipulate product reviews to their advantage. Fake online reviews have a considerable effect on the experiences of online consumers, sellers, and e-commerce platforms. Although there has been academic research focused on identifying fake reviews, there is still a need for studies that thoroughly examine and summarize their origins and impacts. This work introduces a combination of semi-supervised and supervised text mining models to detect fake reviews, comparing their performance using datasets from reviews.

Decoding Sustainability Reporting: Insights from Text Mining and Classification Models for SDGs

Objective: This study aims to investigate the signaling effects of Sustainability Reporting (SR) in listed Singapore firms, particularly in demonstrating firm capitalization and sustainability performance. The research focuses on identifying distinct SR signals using advanced text mining and classification techniques, and their alignment with the United Nations' Sustainable Development Goals (SDGs). Theoretical Framework: The study is grounded in signaling theory, which posits that firms communicate observable characteristics (SR content) to signal unobservable attributes (firm capabilities and sustainability performance). By applying this framework, we analyze how SR may act as a signaling mechanism for large-cap firms and sustainability leaders. Method: This research collects 1,844 sustainability reports from listed Singapore firms between 2016 and 2022. Using a combination of Structural Topic Modeling (STM) and Random Forest (RF) classification models, we extracted and analyzed the key SR signals that differentiate firms by size and sustainability performance. Results: The results indicate that SR signals such as community engagement, climate risk, and compliance are effective in distinguishing between large firms and firms with strong sustainability performance. The Random Forest models achieved high accuracy in identifying these groups. Community engagement, compliance with the Global Reporting Initiative (GRI), and sustainable construction were among the most impactful topics, with large firms focusing more on scope and governance, while sustainability leaders emphasized environmental risks and compliance. Research Implications: The findings provide insights into the practical and theoretical implications of SR as a signaling tool. Key SR topics are identified as critical signals for firms with large capitalization and high sustainability performance, guiding firms in utilizing SR in the context of SDGs. Originality/Value: The findings show that SR topics such as community engagement, climate risk, and compliance serve as key signals for differentiating firms by size and sustainability performance. Firms can strategically emphasize these areas to enhance their SR practices while contributing to broader SDGs.The findings provide insights into the practical and theoretical implications of SR as a signaling tool. Key SR topics are identified as critical signals for firms with large capitalization and high sustainability performance, guiding firms in enhancing their SR strategies.

A novel integrated approach for quantifying the convergence of disruptive technologies from science to technology

With rapid developments in science and technology, knowledge transfer from science to technology and technology convergence from different fields are accelerating. Technology convergence has become a main source of disruptive technologies (DTs). To facilitate enterprise R&D strategic decision-making and government innovation policies formulation, it is necessary to quantify the convergence processes of DTs and understand the DTs' emergence characteristics from science to technology. Existing research on technology convergence measurement mainly used patent citation information, patent co-classification analysis, and text mining. However, since these studies have limited analysis of the sources and causes of technology convergence from the perspective of knowledge memes, resulting in insufficient revelation of the processes and characteristics of DTs' emergence. Knowledge meme theory helps to reveal the relationships between knowledge diffusion, knowledge convergence, and technology convergence. Therefore, in this paper, we proposed a research framework for quantifying the convergence of DTs from science to technology. In this framework, we analyzed the knowledge diffusion and technology convergence of DTs from science to technology based on knowledge meme theory. We also integrated patent citation analysis, text mining, and cascade network models to quantitatively measure knowledge diffusion and technology convergence characteristics. We tried to understand the generation mechanisms of DTs from the perspective of technology convergence. We took smartphones as a case study to verify the framework's validity and flexibility. This paper provides a novel approach for quantifying the convergence of DTs from science to technology, which can help us to understand the emergence and development trends of DTs. This paper will also be of interest to smartphone technology R&D experts.

Stance Detection in the Context of Fake News—A New Approach

Online social networks (OSNs) are inundated with an enormous daily influx of news shared by users worldwide. Information can originate from any OSN user and quickly spread, making the task of fact-checking news both time-consuming and resource-intensive. To address this challenge, researchers are exploring machine learning techniques to automate fake news detection. This paper specifically focuses on detecting the stance of content producers—whether they support or oppose the subject of the content. Our study aims to develop and evaluate advanced text-mining models that leverage pre-trained language models enhanced with meta features derived from headlines and article bodies. We sought to determine whether incorporating the cosine distance feature could improve model prediction accuracy. After analyzing and assessing several previous competition entries, we identified three key tasks for achieving high accuracy: (1) a multi-stage approach that integrates classical and neural network classifiers, (2) the extraction of additional text-based meta features from headline and article body columns, and (3) the utilization of recent pre-trained embeddings and transformer models.

How loud is consumer voice in product deletion decisions? Retail analytic insights

This study examines the role of online consumer reviews in product deletion decisions. Building upon product portfolio management theory and the signaling theory, we integrate consumer voice, represented by online consumer review behavior into organizational voice—strategic product deletion decision-making. We empirically evaluated the relationship between online consumer reviews and organizational product deletion decisions using text mining and logistic regression models. The results indicate consumer online review characteristics are significant factors for product deletion decisions. Findings suggest that products with lower review attribute ratings, or those with textual review content less pertinent to the core performance attributes, are more likely to be deleted. The linguistic retail analytic characteristics of online reviews also provide insights for product deletion decisions. Products with reviews having higher subjectivity, shorter length, and lower readability are more likely to be deleted. Pre-purchase consumer voice—the perceived helpfulness or unhelpfulness of online reviews also impacts product deletion decisions. A general conclusion is that online reviews can provide important retail analytics for smarter retail operations planning at the strategic and tactical levels when it comes to product planning and portfolio management through product deletion.

Leveraging artificial intelligence and machine learning analytics for development effectiveness: a comprehensive approach to extract insights from project data

ABSTRACT In the normal course of business, international development institutions investing in development projects generate thousands of project-related documents summarising and analysing each aspect of their policymaking processes and policy lifecycles from design and financing through implementation performance and ultimately project/policy outputs, outcomes and effectiveness-related data. Moreover, institutions’ internal processes for quality assurance, monitoring and results measurement systems generate quantitative and qualitative primary and secondary data that can be employed to extract insights about lessons learned, internal decision-making processes, business model changes and project and portfolio performance. Resource and time constraints, however, result in the underutilisation of these valuable data sources for knowledge management, planning, evaluation and analysis. Specifically, qualitative insights housed in project documents remain largely inaccessible and cannot be employed systematically in combination with other quantitative data, in a unified framework. This article explores how machine learning can accelerate knowledge generation and management and aid results-based decision-making in line with development institutions’ existing development effectiveness frameworks through two main channels. The first leverages project documentation for historical portfolio systematisation to extract key strategic topics as well as lessons learned through the application of techniques such as text mining and topic modelling. The second proposes an agency-based system for predictive analytics, which analyses current and historical data to make predictions about future outcomes or trends to strengthen data-driven decision-making.

Investigating various cryptocurrency research trends: an analysis employing text mining and topic modeling

Purpose The trend among the financial investors to integrate cryptocurrencies, the very first completely digital assets, in their investment portfolio, has increased during the last decade. Even though cryptocurrencies share certain common characteristics with other investment products, they have their own distinct characteristic features, and the behavior of this asset class is currently being studied by the research scholars interested in this domain. Design/methodology/approach Using the text mining approach, this article examines research trends in the field of cryptocurrencies to identify prospective research needs. To narrow down to ten topics, the abstracts and the indexed keywords of 1,387 research publications on cryptocurrency, blockchain and Bitcoins published between 2013 and 2022 were analyzed using the topic modeling technique and Latent Dirichlet allocation (LDA). Findings The findings show a wide range of study trends on various aspects of cryptocurrencies. In the recent years, there have been lots of research and publications on the topics such as cryptocurrency markets, cryptocurrency transactions and use of blockchain in transactions and security of Bitcoin. In comparison, topics such as use of blockchain in fintech, cryptocurrency regulations, blockchain smart contract protocols and legal issues in cryptocurrency have remained relatively underexplored. After using the LDA, this paper further analyzes the significance of each topic, future directions of individual topics and its popularity among researchers in the discussion section. Originality/value While similar studies exist, no other work has used topic modeling to comprehensively analyze the cryptocurrencies literature by considering diverse fields and domains.

Identifying innovation roadblocks: unveiling knowledge and innovation patterns that hinder commercialisation

ABSTRACT While intellectual property (IP) management is critical for innovation, specific knowledge and innovation patterns within it can obstruct commercialisation. This study explores how these patterns impede the path to market success for emerging innovations. We introduce a novel method to detect and recognise these patterns, offering insights into factors contributing to innovation system failure. Applying the Triple Helix Model, we leverage text mining, network analysis, and structural equation modelling within the Russian pharmaceutical industry. Our research reveals limitations in the triple helix model’s ability to capture problematic innovation patterns. Notably, local-closed and local semi-closed innovation networks emerge as significant barriers to commercialisation, further exacerbated by foreign dominance. While strong actor synergy is crucial, it alone cannot guarantee competitive advantage. Factors like geographical distance, disciplinary silos, and limited external collaboration further hinder success. This study highlights the need for effective knowledge production and collaboration practices, alongside strong synergy, to achieve market-leading innovations. Recognising and addressing these patterns can inform policy decisions, ultimately fostering more robust innovation outcomes, advancing innovation system theory in the process.

Exploring the generative AI adoption in service industry: A mixed-method analysis

In the last few years, many service organisations have been exploring the use of Generative Artificial Intelligence (GAI) tools for their businesses and upgrading their existing processes. These tools have the potential and capability to transform the business world in various aspects. However, serval service organisations are facing many challenges while adopting the GAI tools in their organisations. In a similar context, this study explores the adoption of GAI barriers through two studies by a mixed-method approach. The first study is based on YouTube datasets of selected videos where GAI adoption challenges, problems, and barriers were discussed. Further, these YouTube datasets were analysed through text mining and empirical modelling techniques. In the second study, an extensive literature review was done and critical barriers to GAI adoption were identified based on the extensive literature review. Further, these barriers were analysed through three theoretical lenses and a hybrid fuzzy multicriteria decision-making approach. In addition, the results from the first study were further matched and verified with our second study. This establishes the relevance of adopting a mixed-method approach. Our major findings are: (i) trust, anticipation, and surprise emerged as the strongest emotions of the viewers who posted their comments on the YouTube videos; (ii) Five major barriers are revealed through topic analysis of YouTube transcripts and these are ethical, technological, regulations & policies, cost, and human resources; (iii) Six major barriers are identified through second study are privacy & security, return on investment, running cost, misuse, over-reliance, and Lack of digital infrastructure.

Mapping of specialized metabolite terms onto a plant phylogeny using text mining and large language models.

Plants produce a staggering array of chemicals that are the basis for organismal function and important human nutrients and medicines. However, it is poorly defined how these compounds evolved and are distributed across the plant kingdom, hindering a systematic view and understanding of plant chemical diversity. Recent advances in plant genome/transcriptome sequencing have provided a well-defined molecular phylogeny of plants, on which the presence of diverse natural products can be mapped to systematically determine their phylogenetic distribution. Here, we built a proof-of-concept workflow where previously reported diverse tyrosine-derived plant natural products were mapped onto the plant tree of life. Plant chemical-species associations were mined from literature, filtered, evaluated through manual inspection of over 2500 scientific articles, and mapped onto the plant phylogeny. The resulting "phylochemical" map confirmed several highly lineage-specific compound class distributions, such as betalain pigments and Amaryllidaceae alkaloids. The map also highlighted several lineages enriched in dopamine-derived compounds, including the orders Caryophyllales, Liliales, and Fabales. Additionally, the application of large language models, using our manually curated data as a ground truth set, showed that post-mining processing can largely be automated with a low false-positive rate, critical for generating a reliable phylochemical map. Although a high false-negative rate remains a challenge, our study demonstrates that combining text mining with language model-based processing can generate broader phylochemical maps, which will serve as a valuable community resource to uncover key evolutionary events that underlie plant chemical diversity and enable system-level views of nature's millions of years of chemical experimentation.

MiPRIME: an integrated and intelligent platform for mining primer and probe sequences of microbial species.

Accurately detecting pathogenic microorganisms requires effective primers and probe designs. Literature-derived primers are a valuable resource as they have been tested and proven effective in previous research. However, manually mining primers from published texts is time-consuming and limited in species scop. To address these challenges, we have developed MiPRIME, a real-time Microbial Primer Mining platform for primer/probe sequences extraction of pathogenic microorganisms with three highlights: (i) comprehensive integration. Covering >40 million articles and 548942 organisms, the platform enables high-frequency microbial gene discovery from a global perspective, facilitating user-defined primer design and advancing microbial research. (ii) Using a BioBERT-based text mining model with 98.02% accuracy, greatly reducing information processing time. (iii) Using a primer ranking score, PRscore, for intelligent recommendation of species-specific primers. Overall, MiPRIME is a practical tool for primer mining in the pan-microbial field, saving time and cost of trial-and-error experiments. The web is available at {{https://www.ai-bt.com}}.

A framework for process risk assessment incorporating prior hazard information in text mining models using chunking

In process industries, complexity of operations and continuous exposure to hazardous substances, equipment and environment necessitates performing fault detection and diagnosis (FDD), and risk assessment via accident/failure modelling. Safety reports contain important information regarding health of process systems, hence FDD and risk assessment by text mining of reports is vital to identify potential faults, reveal insights on their behaviour/interactions, and predict hazard escalation into incidents. Here a novel hybrid framework is proposed where accident theory and hazard information are combined with text mining of incident descriptions to perform FDD and accident modelling. Information about hazards and failure events is used to generate syntactic rules of accident causation which are used to extract text chunks from incident descriptions depicting constituent faults/process safety events. Then an ensemble of unsupervised/semi-supervised models is applied on the chunks to identify hazardous elements and develop chain of events and fault trees showcasing failure propagation. The framework is applied on incident investigation reports of an Indian steel plant and 56 chains of events and corresponding 13 fault trees are identified. A comparison of the results generated by the framework with actual inputs provided by the HSE team of the plant showed accuracy of 85.42 %.

Automatic text classification of drug-induced liver injury using document-term matrix and XGBoost.

Regulatory agencies generate a vast amount of textual data in the review process. For example, drug labeling serves as a valuable resource for regulatory agencies, such as U.S. Food and Drug Administration (FDA) and Europe Medical Agency (EMA), to communicate drug safety and effectiveness information to healthcare professionals and patients. Drug labeling also serves as a resource for pharmacovigilance and drug safety research. Automated text classification would significantly improve the analysis of drug labeling documents and conserve reviewer resources. We utilized artificial intelligence in this study to classify drug-induced liver injury (DILI)-related content from drug labeling documents based on FDA's DILIrank dataset. We employed text mining and XGBoost models and utilized the Preferred Terms of Medical queries for adverse event standards to simplify the elimination of common words and phrases while retaining medical standard terms for FDA and EMA drug label datasets. Then, we constructed a document term matrix using weights computed by Term Frequency-Inverse Document Frequency (TF-IDF) for each included word/term/token. The automatic text classification model exhibited robust performance in predicting DILI, achieving cross-validation AUC scores exceeding 0.90 for both drug labels from FDA and EMA and literature abstracts from the Critical Assessment of Massive Data Analysis (CAMDA). Moreover, the text mining and XGBoost functions demonstrated in this study can be applied to other text processing and classification tasks.

Collective actors and potential alliances for eco-social policies in Germany

To break the vicious circle of mutually reinforcing climate and social crises, there is a rapidly growing literature around integrated public policy instruments called eco-social policies. The actors potentially drive such policies in public debate and the policy process remains under-researched. This paper elaborates on the positioning of various non-state actors on eco-social policies and potential alliance-building in Germany. It derives hypotheses from the existing literature on the role of trade unions, social- and environmental non-governmental organizations, and social movements in eco-social transformation. It tests them empirically on a dataset of public communication and uses a combination of computer-assisted text-analytic tools, namely text mining and structural topic modeling. The findings indicate that although eco-social themes as cross-cutting issues offer good conditions for alliance-building, actors differ widely in their potential to do so. Based on actors’ eco-social broadness and transformational intensity, the paper finds four clusters: a status quo supporter, an activist, a pragmatic, and an eco-social alliance cluster and discusses possible strategies for them. The findings highlight the relevance of service sector unions and social non-governmental organizations as they could act as a bridge to connect social and ecological interests. The paper’s contribution to the Special Issue is twofold: It addresses the policy dimension by examining what issues actors raise about ecological and social concerns. In terms of politics, it gains insights into actors’ positioning and their strategic alliance-building. Both shed light on the potential for eco-social change.

The Discursive Dimensions of Pernicious Polarization. Analysis of Right-Wing Populists in Western Europe on Twitter

The objective of this research is to explore the political discourse of West European right-wing populist leaders in the perspective of pernicious polarization, focusing on their positions and argumentation styles. To achieve this, over 50,000 tweets from right-wing populist leaders in Western Europe (Italy, France and Spain) were collected for a period spanning from 2 July 2019, which marks the beginning of the 9th legislature of the European Parliament, to 2 July 2023. Employing Text Mining and Topic Modeling techniques, this research will reconstruct and comparatively analyze the topics addressed by the leaders from different countries and the dynamics of polarization discourse proposing an exploratory study aiming to locate the words of pernicious polarization used by each leader.

Intelligent Geo-Tour Route Recommendation Algorithm Based on Feature Text Mining and Spatial Accessibility Model

In view of the problems in planning and recommending tour routes, this paper constructs a feature text mining (FTM) method and spatial accessibility model (SAM) as the key factors for scenic spot recommendation (SSR) and tour route recommendation (TRR). The scenic spot clustering algorithm (SSCA) based on FTM was constructed by tourists’ text evaluation data mining. Considering the spatial attributes of scenic spots, the scenic spot topology tree algorithm (SSTTA) based on dynamic buffer spatial accessibility (DBSA) was constructed. The optimal scenic spots were recommended based on interest matching and spatial accessibility optimization. As to the recommended scenic spots, this paper proposes an optimal tour route recommendation algorithm (TRRA) based on SSTTA, which aims to determine the optimal adjacent section path structure tree (ASPST) with the lowest cost under travel constraints and transportation modes. The experiment verifies that the proposed algorithm can recommend scenic spots that match tourists’ interests and have optimal spatial accessibility, and the optimal tour routes with the lowest costs under certain travel constraints. Compared with the searched sub-optimal tour routes, the optimal tour route recommended by the proposed algorithm produces the lowest travel costs, and all the scenic spots in the tour route meet the tourists’ interests. Compared with the commonly used BDMA and GDMA methods, the proposed algorithm can determine the optimal routes with lower travel costs.

Text Mining and Financial Analysis Modeling for Financial Statement Disclosure

This paper explores the integration of financial analysis, text mining, and blockchain technology to enhance financial statement disclosure and analysis processes. Leveraging text mining algorithms, the study extracts valuable insights from unstructured financial data, unveiling hidden patterns and sentiments within financial statements. Additionally, blockchain technology is employed to ensure secure and immutable storage of financial data, fostering transparency and trust in financial transactions and disclosures. Through the automation and digitization of financial reporting processes, stakeholders can streamline financial statement analysis, identify risks and opportunities, and make data-driven decisions with greater accuracy and efficiency.

Customer Feedback Analysis Using Text Mining

Complexity surrounding the holistic nature of customer experience has made measuring customer perceptions of interactive service experiences challenging. At the same time, advances in technology and changes in methods for collecting explicit customer feedback are generating increasing volumes of unstructured textual data, making it difficult for managers to analyze and interpret this information. Consequently, text mining, a method enabling automatic extraction of information from textual data, is gaining in popularity. However, this method has performed below expectations in terms of depth of analysis of customer experience feedback and accuracy. In this study, we advance linguistics-based text mining modeling to inform the process of developing an improved framework. The proposed framework incorporates important elements of customer experience, service methodologies and theories such as co-creation processes, interactions and context. This more holistic approach for analyzing feedback facilitates a deeper analysis of customer feedback experiences, by encompassing three value creation elements: activities, resources, and context (ARC). Empirical results show that the ARC framework facilitates the development of a text mining model for analysis of customer textual feedback that enables companies to assess the impact of interactive service processes on customer experiences. The proposed text mining model shows high accuracy levels and provides flexibility through training. As such, it can evolve to account for changing contexts over time and be deployed across different (service) business domains; we term it an “open learning” model. The ability to timely assess customer experience feedback represents a pre-requisite for successful co-creation processes in a service environment.

Text mining of hypertension researches in the west Asia region: a 12-year trend analysis

More than half of the world population lives in Asia and hypertension (HTN) is the most prevalent risk factor found in Asia. There are numerous articles published about HTN in Eastern Mediterranean Region (EMRO) and artificial intelligence (AI) methods can analyze articles and extract top trends in each country. Present analysis uses Latent Dirichlet allocation (LDA) as an algorithm of topic modeling (TM) in text mining, to obtain subjective topic-word distribution from the 2790 studies over the EMRO. The period of checked studied is last 12 years and results of LDA analyses show that HTN researches published in EMRO discuss on changes in BP and the factors affecting it. Among the countries in the region, most of these articles are related to I.R Iran and Egypt, which have an increasing trend from 2017 to 2018 and reached the highest level in 2021. Meanwhile, Iraq and Lebanon have been conducting research since 2010. The EMRO word cloud illustrates ‘BMI’, ‘mortality’, ‘age’, and ‘meal’, which represent important indicators, dangerous outcomes of high BP, and gender of HTN patients in EMRO, respectively.