Search results

The aim of this work is to increase awareness of the potential of the technique of text mining to discover knowledge and further promote research collaboration between knowledge management and the information technology communities. Since its emergence, text mining has involved multidisciplinary studies, focused primarily on database technology, Web-based collaborative writing, text analysis, machine learning and knowledge discovery. However, owing to the large amount of research in this field, it is becoming increasingly difficult to identify existing studies and therefore suggest new topics.

This article offers a systematic review of 85 academic outputs (articles and books) focused on knowledge discovery derived from the text mining technique. The systematic review is conducted by applying “text mining at the term level, in which knowledge discovery takes place on a more focused collection of words and phrases that are extracted from and label each document” (Feldman et al., 1998, p. 1).

The results revealed that the keywords extracted to be associated with the main labels, id est, knowledge discovery and text mining, can be categorized in two periods: from 1998 to 2009, the term knowledge and text were always used. From 2010 to 2017 in addition to these terms, sentiment analysis, review manipulation, microblogging data and knowledgeable users were the other terms frequently used. Besides this, it is possible to notice the technical, engineering nature of each term present in the first decade. Whereas, a diverse range of fields such as business, marketing and finance emerged from 2010 to 2017 owing to a greater interest in the online environment.

This is a first comprehensive systematic review on knowledge discovery and text mining through the use of a text mining technique at term level, which offers to reduce redundant research and to avoid the possibility of missing relevant publications.

The COVID-19 epidemic has brought attention to the variables that influence the mental health of health workers who are entrusted with nursing individuals. Despite the fact that many articles have examined the effects of social media usage on mental health, there is a lack of research synthesizing learning from this body of research. The purpose of this study is to use text mining and citation-based bibliometric analysis to conduct a detailed review of extant literature on health workers’ mental health and social networking habits.

This study conducts a full-text analysis of 36 articles selected on health workers' mental health and social media using text-mining techniques in R programming and a bibliometric citation analysis of 183 papers from the Scopus database in VOS viewer software. But the limitations of the methods used in this study are that the bibliometric analysis was limited to the Scopus database because the VOS viewer program did not support any other database and the text-mining approach caused the natural processing redundancy.

The bibliometric analysis reveals the thematic networks that exist in the literature of health workers’ mental health and social networking. The findings from text mining identified ten topic models, which helped to find the related papers classified in ten different groups and are provided alongside a summary of the published research and a list of the primary authors with posterior probability through Latent Dirichlet Allocation.

To the best of the authors’ knowledge, this is the first hybrid review, combining text mining and bibliometric review, on health workers’ mental health where social networking plays a moderating role. This paper critically provides an overview of the impact of social networking on health workers' mental health, presents the most important and frequent topics, introduces the scientific visualization of articles published in the Scopus database and suggests further research avenues. These findings are important for academics, health practitioners and medical specialists interested in learning how to better support the mental health of health workers using social media.

Purpose: The main aim of the study is to provide a tool for non-financial information in decision-making. We analysed the non-financial data in the annual reports in order to show the usage of this information in financial decision processes.

Need for the Study: Main financial reports such as balance sheets and income statements can be analysed by statistical methods. However, an expanded financial reporting framework needs new analysing methods due to unstructured and big data. The study offers a solution to the analysis problem that comes with non-financial reporting, which is an essential communication tool in corporate reporting.

Methodology: Text mining analysis of annual reports is conducted using software named R. To simplify the problem, we try to predict the companies’ corporate governance qualifications using text mining. K Nearest Neighbor, Naive Bayes and Decision Tree machine learning algorithms were used.

Findings: Our analysis illustrates that K Nearest Neighbor has classified the highest number of correct classifications by 85%, compared to 50% for the random walk. The empirical evidence suggests that text mining can be used by all stakeholders as a financial analysis method.

Practical Implications: Combining financial statement analyses with financial reporting analyses will decrease the information asymmetry between the company and stakeholders. So stakeholders can make more accurate decisions. Analysis of non-financial data with text mining will provide a decisive competitive advantage, especially for investors to make the right decisions. This method will lead to allocating scarce resources more effectively. Another contribution of the study is that stakeholders can predict the corporate governance qualification of the company from the annual reports even if it does not include in the Corporate Governance Index (CGI).

The paper's aim is to mine and analyze opinion formation on the basis of consumer dialogs in online forums.

The study identifies opinions, communication relationships, and dialog acts of forum users using different text mining methods. Utilizing this data, social networks can be derived and analyzed to detect influential users and opinion tendencies. The approach is applied to sample online forums discussing the iPhone.

Combining text mining and social network analysis enables the study of opinion formation and yields encouraging results. Out of the four methods employed for text mining, support vector machines performed best.

The data set applied here is fairly small. More threads on different products will be considered in future work to improve validation.

The approach represents a valuable instrument for online market research. It enables companies to recognize opportunities and risks and to initiate appropriate marketing actions.

This work is one of the first studies that combine communication content, relationships and dialog acts for analyzing opinion formation.

The purpose of this study is to explore to which extent data mining research would be associated with the library and information science (LIS) discipline. This study aims to identify data mining related subject terms and topics in representative LIS scholarly publications.

A large set of bibliographic records over 38,000 was collected from a scholarly database representing the fields of LIS and the data mining, respectively. A multitude of text mining techniques were applied to investigate prevailing subject terms and research topics, such as influential term analysis and Dirichlet multinomial regression topic modeling.

The findings of this study revealed the relationship between the LIS and data mining research domains. Various data mining method terms were observed in recent LIS publications, such as machine learning, artificial intelligence and neural networks. The topic modeling result identified prevailing data mining related research topics in LIS, such as machine learning, deep learning, big data and among others. In addition, this study investigated the trends of popular topics in LIS over time in the recent decade.

This investigation is one of a few studies that empirically investigated the relationships between the LIS and data mining research domains. Multiple text mining techniques were employed to delineate to which extent the two research domains would be associated with each other based on both at the term-level and topic-level analysis. Methodologically, the study identified influential terms in each domain using multiple feature selection indices. In addition, Dirichlet multinomial regression was applied to explore LIS topics in relation to data mining.

This paper aims to equip professionals and researchers in the fields of advertising, branding, public relations, marketing communications, social media analytics and marketing with a simple, effective and dynamic means of evaluating consumer behavioural sentiments and engagement through Arabic language and script, in vivo.

Using quantitative and qualitative situational linguistic analyses of Classical Arabic, found in Quranic and religious texts scripts; Modern Standard Arabic, which is commonly used in formal Arabic channels; and dialectical Arabic, which varies hugely from one Arabic country to another: this study analyses rich marketing and consumer messages (tweets) – as a basis for developing an Arabic language social media methodological tool.

Despite the popularity of Arabic language communication on social media platforms across geographies, currently, comprehensive language processing toolkits for analysing Arabic social media conversations have limitations and require further development. Furthermore, due to its unique morphology, developing text understanding capabilities specific to the Arabic language poses challenges.

This study demonstrates the application and effectiveness of the proposed methodology on a random sample of Twitter data from Arabic-speaking regions. Furthermore, as Arabic is the language of Islam, the study is of particular importance to Islamic and Muslim geographies, markets and marketing.

The findings suggest that the proposed methodology has a wider potential beyond the data set and health-care sector analysed, and therefore, can be applied to further markets, social media platforms and consumer segments.

To remedy these gaps, this study presents a new methodology and analytical approach to investigating Arabic language social media conversations, which brings together a multidisciplinary knowledge of technology, data science and marketing communications.

This study explores the levels of Facebook engagement of the two largest Europe-based shipping lines, Maersk and Mediterranean Shipping Company (MSC), to discover the marketing orientation of the topics advertised and to ascertain whether they tend to be about brand recognition, new transport services, or value propositions for stakeholders.

The Facebook posts of Maersk and MSC were analysed using social media text mining and social network analysis (SNA); in- and out-degree centrality analysis was performed to determine the key terms in their posts. NetMiner software was used to collect the respective data on Maersk and MSC. The inquiry period was set between May 2020 and February 2021.

The results indicated a divergence in their post contents, with higher engagement and a wider, more active follower base for MSC than for Maersk. Maersk primarily posts about logistics services and supply chain solutions. MSC communicates about new and large container vessels. Both companies seek greater brand recognition and information sharing through social media.

These results can be used by the stakeholders to evaluate whether Maersk and MSC truly deliver on their respective value propositions communicated online through their social media engagement. It can also help Maersk and MSC gauge the level of effectiveness of their communication with stakeholders and modify their digital engagement strategy accordingly.

Based on the text mining tools, this paper aims to propose a new method to evaluate the subjectivity and objectivity of corporate social responsibility information disclosure.

The authors build up a text subjectivity evaluation model of corporate social responsibility reports through meta-analysis; a text mining is conducted to all sample CSR reports released by Chinese listed companies untill March 2016[1]. Furthermore, the authors made an overall and quantitative analysis of the situation which contained changing state, characteristics and abnormal value on the subjectivity and objectivity of information disclosure.

The results show that the subjectivity scores of social responsibility reports of Chinese listed companies are generally in a normal distribution. The diagram turns out to be a rising trend over the years and increases linearly from 2011 to 2013. Also, the industry heterogeneity and policy control are the main reasons for the formation of the differences, which are significant between different industries and different years.

This paper provides not only an important empirical basis for the research of corporate social responsibility but also a new idea for the non-financial information disclosure as well as objective evaluation of normative text.

COVID-19, a causative agent of the potentially fatal disease, has raised great global public health concern. Information spreading on the COVID-19 outbreak can strongly influence people behaviour in social media. This paper aims to question of information spreading on COVID-19 outbreak are addressed with a massive data analysis on Twitter from a multidimensional perspective.

The evolutionary trend of user interaction and the network structure is analysed by social network analysis. A differential assessment on the topics evolving is provided by the method of text clustering. Visualization is further used to show different characteristics of user interaction networks and public opinion in different periods.

Information spreading in social media emerges from different characteristics during various periods. User interaction demonstrates multidimensional cross relations. The results interpret how people express their thoughts and detect topics people are most discussing in social media.

This study is mainly limited by the size of the data sets and the unicity of the social media. It is challenging to expand the data sets and choose multiple social media to cross-validate the findings of this study.

This paper aims to find the evolutionary trend of information spreading on the COVID-19 outbreak in social media, including user interaction and topical issues. The findings are of great importance to help government and related regulatory units to manage the dissemination of information on emergencies, in terms of early detection and prevention.

Data mining has been a popular research area in the past decades. Many researchers study data-mining theories, methods, applications and trends; however, there are very few studies on data-mining-related topics in social media. This paper aims to explore the topics related to data mining based on the data collected from Wikipedia.

In total, 402 data-mining-related articles were obtained from Wikipedia. These articles were manually classified into several categories by the coding method. Each category formed an article-term matrix. These matrices were analysed and visualized by the self-organizing map approach. Several clusters were observed in each category. Finally, the topics of these clusters were extracted by content analysis.

The articles obtained were classified into six categories: applications, foundation and concepts, methodologies, organizations, related fields and topics and technology support. Business, biology and security were the three prominent topics of the applications category. The technologies supporting data mining were software, systems, databases, programming languages and so forth. The general public was more interested in data-mining organizations than the researchers. They also focused on the applications of data mining in business more than in other fields.

This study will help researchers gain insight into the general public’s perceptions of data mining and discover the gap between the general public and themselves. It will assist researchers in finding new techniques and methods which will potentially provide them with new data-mining methods and research topics.