Qualitative Text Analysis Supported by Conceptual Data Systems

Content analysis as a method in social sciences is used to systematically explore textual data. Data resulting from content analysis can be made transparent by saving it in a conceptual data system. This supports its interpretation and reexamination and the process of interpretative theory building. By means of an example of a conceptual data system from musicology, the possibilities and restrictions of this new approach in computer-aided qualitative text research are analyzed. Finally, the approach is discussed as a general method of qualitative formal theory building in the context of content analysis.     

A Conceptual Framework for Quantitative Text Analysis

Quantitative text analysis refers tothe application of one or more methods for drawingstatistical inferences from text populations. Afterbriefly distinguishing quantitative text analysisfrom linguistics, computational linguistics, andqualitative text analysis, issues raised during the1955 Allerton House Conference are used as a vehiclefor characterizing classical text analysis as aninstrumental-thematic method. Quantitative textanalysis methods are then depicted according to a2 × 3 conceptual framework in which texts areinterpreted either instrumentally (according to theresearcher's conceptual framework) orrepresentationally (according to the texts' sources'perspectives), as well as in which variables arethematic (counts of word/phrase occurrences),semantic (themes within a semantic grammar), ornetwork-related (theme- or relation-positions withina conceptual network). Common methodological errorsassociated with each method are discussed. Thepaper concludes with a delineation of the universeof substantive answers that quantitative text analysisis able to provide to social science researchers.     

Identification of future signal based on the quantitative and qualitative text mining: a case study on ethical issues in artificial intelligence

To foresee the advent of new technologies and their socio-economic impact is a necessity for academia, governments and private enterprises as well. In the future studies, the identification of future signal is one of the renowned techniques for analysis of trends, emerging issue, and gaining future insights. In the Big Data era, recent scholars have proposed using a text mining procedure focusing upon web data such as new social media and academic papers. However, the detection of future signals is still under a developing area of research, and there is much to improve existing methodology as well as developing theoretical foundations. The present study reviews previous literature on identifying emerging issue based on the weak signal detection approach. Then the authors proposed a revised framework that incorporate quantitative and qualitative text mining for assessing the strength of future signals. The authors applied the framework to the case study on the ethical issues of artificial intelligence (hereafter AI). From EBSCO host database, the authors collected text data covering the ethical issues in AI and conducted text mining analysis. Results reveal that emerging ethical issues can be classified as strong signal, weak signal, well-known but not so strong signal, and latent signal. The revised methodology will be able to provide insights for government and business stakeholders by identifying the future signals and their meanings in various fields.     

Computer assisted text analysis in the social sciences

We use the term “Computer Assisted Text Analysis” in a broad sense to refer to a range of current techniques from quantitative social science and content analysis to ‘data mining’ and ‘text classification’, including the analysis of open-ended survey questions, transcribed interviews and speeches, wherever, in fact, the researcher is confronted with data in the form of natural language texts of social scientific interest. These methods are often used in exploratory data analysis, but can also be applied systematically with moderate statistical rigour in the development and testing of hypotheses at various theoretical levels, ranging from the statistics of word usage to changes within or between discourses over time. The general approach is in the tradition of content analysis, by which words which occur together in relatively close proximity in the same context are interpreted as relating to a common theme or concept in the discourse studied. We review a comprehensive set of tools to identify and visualize structures of co-occurrence of words and concepts both within, and in comparing, a number of texts. These produce results not essentially different from those reached by representing word co-occurrences in terms of network analysis or neural network programming using schematic linguistic templates of various kinds. A comparison of the relational data analysis vs. a dictionary-based MDS approach shows that these provide very close if not identical results, despite the fact that the underlying assumptions are frequently represented as different theoretical approaches.     

基本建设投资领域"项目"名词的考证

“项目”一词及其派生词组在基本建设投资领域中的引用非常频繁,由于没有对其进行行业的规范定义,所以使用中常出现混乱,造成词义的误解。通过对“项目”名词的考证,分析了“项目”各种组合名词的内涵限定意义和层次关系,提出了在基本建设投资领域内对“项目”一词及其派生词组的含义认知应统一的意见。     

Using semiotics to analyze representational complexity in social media

Data from social media offer us multimedia data brimming with multiple layers of meanings. Social media enable rapid-fire digital communications. These communications are incredibly complex in content, form and meaning. This representational complexity is a stumbling block in data analysis that stands in the way of deeper explanations. These unstructured data, rich in social meanings, are as complex as the phenomena they represent. While it is possible to formulate an entire research methodology around semiotics, it is not always necessary. We can adapt semiotic analysis within existing methodologies. This paper offers and illustrates an analytical technique to address representational complexity that can be used in conjunction with other methodologies such as case study, ethnography, etc. This analytical technique espouses a critical realist philosophy to develop much needed, deeper explanations from qualitative data.     

Excel spreadsheet as a tool for social narrative analysis

Qualitative research is an open field where different researchers from several disciplines deal with social meanings and with the issue of understanding. During the last two decades, the use of computers and software has extended to become a relevant part of our daily landscape and also a basic device of social research, even in relation to a qualitative approach. There are many applications of qualitative research software specially designed by a diversity of firms and institutions producing different levels of sophisticated tools that can be used in the social research process. This paper presents a protocol for using an Excel spreadsheet as a tool for analyzing social discourses. We will show how to work with the documents produced in the empirical data collection and the criteria to structure the components of the application and its main representations. Finally, we offer a methodology for developing a personalized application in order to orient social design as a powerful and reflexive tool that contribute to a social thinking immersed in continuous improvement.     

Trade-offs and disappearing acts: shifting societal discourses of diversity in Canada over three decades

In the past few decades, research on minority and disadvantaged groups in the workplace has focused on the discourse of diversity management; however, most of this research has emphasized individual and organizational discourse rather than broader, societal contexts. Our critical analysis of societal/macro level discourse explores the discursive constructions of equity and diversity in Canada, and provides original findings on how these discourses have been produced in the public sphere. We apply quantitative and qualitative textual analysis to articles published from 1986 to 2014 in The Globe and Mail, a nationally distributed newspaper, and the Canadian Employment Equity Act Annual Reports from 1988 to 2013. This paper describes a range of discursive patterns including those focusing on compliance-based equity oriented toward social justice as well as voluntary ‘diversity management’ grounded in corporate self-interest. It demonstrates important trade-offs in who is protected and promoted through the contrasting discourses, and in the types of actors legitimizing these discourses. We provide detailed evidence of these patterns by applying Habermas’ Theory of Communicative Action, and conclude with a discussion of implications for practice and for theory that are suggested in our analysis.     

Forecasting election results by studying brand importance in online news

This study uses the semantic brand score, a novel measure of brand importance in big textual data, to forecast elections based on online news. About 35,000 online news articles were transformed into networks of co-occurring words and analyzed by combining methods and tools from social network analysis and text mining. Forecasts made for four voting events in Italy provided consistent results across different voting systems: a general election, a referendum, and a municipal election in two rounds. This work contributes to the research on electoral forecasting by focusing on predictions based on online big data; it offers new perspectives regarding the textual analysis of online news through a methodology which is relatively fast and easy to apply. This study also suggests the existence of a link between the brand importance of political candidates and parties and electoral results.     

A textual analysis of Bank of England growth forecasts

The Bank of England publishes a quarterly Inflation Report that provides numerical forecasts and a text discussion of its assessment of the UK economy. Previous research has evaluated the quantitative forecasts that are included in these reports, but we focus on the qualitative discussion of output growth, by using an in-sample textual analysis procedure to convert these qualitative assessments into a score for each report over the period 2005–2014. We also construct out-of-sample scores for reports before and after this period. We then compare the scores both to real-time output growth data and to the corresponding quantitative projections published by the bank. We find that overall developments in the UK economy were represented accurately in the text of the Inflation Report. Furthermore, efficiency regressions suggest that there is information in the text that could improve the Bank of England’s quantitative nowcasts and one-quarter-ahead forecasts.     

Linking quality & quantity

A fault of many quantitative studies is the inadequate fit between the real-world processes and the formal aspects of the quantitative research designs as seen in their accounting schemes, measurements, and analysis plans. The examples reviewed in this article show how to ameliorate this problem by following the hermeneutically informed strategy of formalization of qualitative texts. Qualitative studies often possess external validity but lack internal validity. Quantitative studies often possess internal validity but lack external validity. By building quantitative studies on formalizations of the qualitative, the resulting research is more likely to possess both external and internal validity. This strategy of formalization will help to avoid two faults in present-day social science — sterility and discontinuity — and will promote the achievement of a dynamic continunity in social research.     

Qualitative research in psychology: misunderstandings about textual analysis

The authors review some of the problems faced by qualitative research in psychology, focusing on the aspects that limit its use and its inclusion in indexed publications. In order to determine whether these problems exist, a case study on textual analysis was performed. The authors conducted a literature search of many databases from the Web of Science (Sciences Citation Index, Social Sciences Citation Index and the Arts and Humanities Citation Index), with the keywords “textual analysis” and “text analysis”. Subsequently, the authors completed an in-depth analysis of a sample of the publications found, reviewing publication aspects, substantive aspects, methodological aspects and contextual aspects. The results showed that “textual analysis” cannot be considered a specific methodology and so the use of this term as a particular technique could be misleading. This highlights the need to create a common vocabulary to facilitate the systematization and dissemination of work done with qualitative methods.     

Representations of Australia in South Korean online news: a qualitative and quantitative approach utilizing Leximancer and Korean keywords in context

This article outlines original empirical research using a quantitative computer-assisted big data approach to survey and evaluate the representation of Australia in popular South Korean online news media sources. This is an exploratory content analysis of news reporting (in Korean and English) on Australia in key Korean digital news media providers and distributors over a six-month-period during which certain key events occurred that drew Korean news media attention to Australia. The research aims to address the fundamental question: what forms and patterns of representation of Australia are present in South Korean online news media? It is designed in large part to understand how Australia is present as a theme in Korean online news, and how this theme is contextualized by associated topics, such as trade, security, or tourism. The quantitative analysis is augmented using a qualitative method: a series of key informant interviews conducted with editors and journalists responsible for the production and prioritization of news. Further, it is interpreted by locating the research in the context of the Australia-South Korea relationship. We summarize the complexities that arise when analyzing large amounts of textual content, especially from two very different languages, discuss the opportunities that arise from mixed methods—by combining big data (breadth) with contextual analysis (depth) and offer suggestions for aspiring researchers.     

Geometry or poetry? Issues of methods and techniques in regional research

This article begins with the assumption that the research and study of geographical, historical, socio-economic and cultural factors of a local community are prerequisites for intervention or developmental policies. Based on the views of Descartes and Hamann, it then goes on to look at the suitability of the methods, tools and techniques a researcher needs to use today in order to get a complete picture. A positive approach of social phenomena claims that social structures decisively affect an individual’s thought and action, and therefore focuses on the study of external factors. In contrast, an interpretative approach aims at understanding the meanings and motives that govern an individual’s life and behavior. The author concludes that research on both macro and micro levels are necessary for the understanding of social phenomena in a local society and the use of methodological pluralism (both quantitative and qualitative methods) is necessary for effective research as it takes into consideration the weight of history and allows the understanding of those factors which govern people’s lives and determine their behavior and interaction.     

Exploring sources and outcomes of trust and commitment to nonprofit organizations: The case of Amnesty International Portugal

The interactions between customers and organizations have been regarded as a core aspect in cocreating and developing new products and practices. The current study explores these interactions in the context of citizens and nonprofit organizations. The study comprises two parts: (a) a qualitative approach using interviews and the analysis of social networks to better understand the organization's social media marketing practices and corresponding outcomes and (b) a quantitative approach to analyze antecedents and outcomes of trust and being committed to participate in a nonprofit organization such as Amnesty International. From the qualitative approach, the findings highlight that Amnesty International uses social media (Facebook) to share information, and citizens tend to consider sharing posts, but they do not express new ideas or interact with the organization. These findings contribute to structure the model analyzed in the second stage of the research. Regarding the qualitative approach, the results show that organizational credibility is the most significant driver of trust followed by communicative ability. Affectively commitment to participation and relationship perception act as outcomes of overall commitment.     

Religiosity as a source of influence on work engagement: a study of the Malaysian Finance industry

Abstract

The majority of work engagement studies have been conducted using a quantitative approach with limited attention to the institutional and social contexts. Meanwhile, the role of religion in shaping people’s philosophy and behaviour in life and work has been gaining attention from management researchers. Studies have revealed the positive impact of religiosity on a number of human resources and organizational outcomes. However, few studies treat religious belief as a job or personal resource from a HRM perspective. This study fills part of this research gap by focusing on the relevant factors that may affect work engagement in the Malaysian Islamic context. Drawing on data from 41 semi-structured interviews with mid-ranking professionals from the finance sector, this study responds to calls for more focus on contexts and for deeper qualitative investigations into individual dynamics that concern religiosity and work engagement. It provides evidence that religiosity plays an important role in work engagement. Our findings have implications for people management in organizations that have a diverse workforce representing multiple religions.     

Incorporating textual information in customer churn prediction models based on a convolutional neural network

This study investigates the value added by incorporating textual data into customer churn prediction (CCP) models. It extends the previous literature by benchmarking convolutional neural networks (CNNs) against current best practices for analyzing textual data in CCP, and, using real life data from a European financial services provider, validates a framework that explains how textual data can be incorporated in a predictive model. First, the results confirm previous research showing that the inclusion of textual data in a CCP model improves its predictive performance. Second, CNNs outperform current best practices for text mining in CCP. Third, textual data are an important source of data for CCP, but unstructured textual data alone cannot create churn prediction models that are competitive with models that use traditional structured data. A calculation of the additional profit obtained from a customer retention campaign through the inclusion of textual information can be used by practitioners directly to help them make more informed decisions on whether to invest in text mining.     

ECONOMETRICS MEETS SENTIMENT: AN OVERVIEW OF METHODOLOGY AND APPLICATIONS

The advent of massive amounts of textual, audio, and visual data has spurred the development of econometric methodology to transform qualitative sentiment data into quantitative sentiment variables, and to use those variables in an econometric analysis of the relationships between sentiment and other variables. We survey this emerging research field and refer to it as sentometrics, which is a portmanteau of sentiment and econometrics. We provide a synthesis of the relevant methodological approaches, illustrate with empirical results, and discuss useful software.     

Wither Qualitative/Quantitative?: Grounds for Methodological Convergence

The qualitative quantitative issue has been given attention in sociological scholarship for decades. Upon theoretical examination of the basis of separations, the commonly used criteria of subjectivity versus objectivity, systematization, quantification and generalization, do not separate. This suggests that the impetus for the qualitative/quantitative issue is more political than intellectual owing to several factors in the practice of sociology: diverse intellectual heritages, the domination of quantitative sociologists in teaching methods and writing methods text books, the proliferation of computer technology in the past 20 years, and separation of theory and method. Advancing sociological methods means transcending the quantitative/qualitative issue and moving on to consider issues like science, validity, causality and multiverse.     

Taking the “Q” Out of Research: Teaching Research Methodology Courses Without the Divide Between Quantitative and Qualitative Paradigms

The purpose of this paper is to provide evidence that the debate between quantitative and qualitative is divisive and, hence, counterproductive for advancing the social and behavioral science field. We advocate that all graduate students learn to utilize and to appreciate both quantitative and qualitative research methodologies. As such, students will develop into pragmatist researchers who are able to utilize both quantitative and qualitative techniques when conducting research. We contend that the best way to accomplish this is by eliminating quantitative research methodology and qualitative research methodology courses from curricula and replacing these with research methodology courses at different levels that simultaneously teach both quantitative and qualitative techniques within a mixed methodological framework.An earlier version of this article received the 2003 Southwest Educational Research Association (SERA) Outstanding Paper Award.