Text Analytics Approach Research Articles

Strengthening move analysis methodology towards bridging the function-form gap

Move analysis is a text analytical approach first developed by John Swales (1981) to investigate the underlying generic structure of research articles (RAs) in terms of moves-and-steps for pedagogical purposes. A widely shared aspiration of move analysts has been to identify the linguistic features characterizing the various RA moves not only in English, but also across languages. One shortcoming blocking this advancement is the lack of multilingual corpora fully annotated for their specific communicative functions in a coordinated and reliable manner. In this paper, we describe and discuss a methodology for analysing the various RA sections for their generic structure up from the step level in two languages and across a wide range of disciplines, using the discussion section as a test case for illustrating that methodology. Among the topics treated are establishing criteria for choosing a suitable sample of comparable RA discussions across the two languages, designing a model for annotating the section's moves and steps, creating an accessible computer-assisted coding scheme, achieving good levels of inter-rater reliability, and obtaining validation from expert informants and writers. In essence, this is a methodology paper offered as a working model for other EAP researchers undertaking similar analyses in future.

Risk of bias reporting in the recent animal focal cerebral ischaemia literature.

Background: Findings from in vivo research may be less reliable where studies do not report measures to reduce risks of bias. The experimental stroke community has been at the forefront of implementing changes to improve reporting, but it is not known whether these efforts are associated with continuous improvements. Our aims here were firstly to validate an automated tool to assess risks of bias in published works, and secondly to assess the reporting of measures taken to reduce the risk of bias within recent literature for two experimental models of stroke.Methods: We developed and used text analytic approaches to automatically ascertain reporting of measures to reduce risk of bias from full-text articles describing animal experiments inducing middle cerebral artery occlusion (MCAO) or modelling lacunar stroke.Results: Compared with previous assessments, there were improvements in the reporting of measures taken to reduce risks of bias in the MCAO literature but not in the lacunar stroke literature. Accuracy of automated annotation of risk of bias in the MCAO literature was 86% (randomization), 94% (blinding) and 100% (sample size calculation); and in the lacunar stroke literature accuracy was 67% (randomization), 91% (blinding) and 96% (sample size calculation).Discussion: There remains substantial opportunity for improvement in the reporting of animal research modelling stroke, particularly in the lacunar stroke literature. Further, automated tools perform sufficiently well to identify whether studies report blinded assessment of outcome, but improvements are required in the tools to ascertain whether randomization and a sample size calculation were reported.

The Aberdeen Burgh Records of 1398–1531 and the Semantic Web

Abstract This paper provides an overview of two text analytic projects on the Aberdeen burgh records, which are legal records of the city of Aberdeen, Scotland. These records contain detailed information about a range of activities in the city and their legal treatment. The projects cover the periods 1398–1511 (Law in the Aberdeen Council Registers project – LACR) and 1530–1531 (A Text Analytic Approach to Rural and Urban Legal Histories project – TAHL). The completed TAHL project annotated a selected corpus with rich semantic information for the purpose of facilitating historical research by querying and extracting data from across the corpus. The LACR project, which is ongoing, focuses on transcribing the first eight volumes of the Aberdeen burgh records (1398–1511) into the Text Encoding Initiative’s standard, thus making the text machinereadable. This project lays the foundation for further analysis and enrichment of the corpus.

Letter from the Editors: Special Issue on the 2017 Peter J. Buckley and Mark Casson AIB Dissertation Award

This editorial article introduces the AIB Insights special dedicated to the 2017 Peter J. Buckley and Mark Casson AIB Dissertation Award. The issue includes “Three Essays on Corruption, Government Transparency and Foreign Direct Investment” by Neli Kouneva Loewenthal; “Three Essays on the Influence of Political Connections on Firm International Expansion Strategy” by João Albino-Pimentel; “Responses to Subpar Performance in Foreign Subsidiaries” by Vanessa C. Hasse; “Managing Complex Multinational Enterprises: Internal Network Structure and Expatriation Strategies” by Jong Min Lee; and “A Text Analytic Approach to Study Host Country Nationalist Sentiments and MNE Responses during National Conflicts” by Xiaocong Tian.

A Text Analytic Approach to Study Host Country Nationalist Sentiments and MNE Responses during National Conflicts

International business scholars have conducted lots of studies on MNE strategic choices in host country. However, most of the strategic choices are those need a long time to be implemented and to take effect, and we known little about how MNEs can instantly respond to host country environmental changes. Using social media textual data, I focus on nationalist sentiment and develop two types of nationalist sentiment, namely expressive nationalist sentiment and instrumental nationalist sentiment, through textual analysis. Then, I examine what rhetorical strategies MNEs adopt when different types of nationalist sentiment are high.

Big data text analytics: an enabler of knowledge management

PurposeThe purpose of this paper is to examine the role of big data text analytics as an enabler of knowledge management (KM). The paper argues that big data text analytics represents an important means to visualise and analyse data, especially unstructured data, which have the potential to improve KM within organisations.Design/methodology/approachThe study uses text analytics to review 196 articles published in two of the leading KM journals – Journal of Knowledge Management and Journal of Knowledge Management Research & Practice – in 2013 and 2014. The text analytics approach is used to process, extract and analyse the 196 papers to identify trends in terms of keywords, topics and keyword/topic clusters to show the utility of big data text analytics.FindingsThe findings show how big data text analytics can have a key enabler role in KM. Drawing on the 196 articles analysed, the paper shows the power of big data-oriented text analytics tools in supporting KM through the visualisation of data. In this way, the authors highlight the nature and quality of the knowledge generated through this method for efficient KM in developing a competitive advantage.Research limitations/implicationsThe research has important implications concerning the role of big data text analytics in KM, and specifically the nature and quality of knowledge produced using text analytics. The authors use text analytics to exemplify the value of big data in the context of KM and highlight how future studies could develop and extend these findings in different contexts.Practical implicationsResults contribute to understanding the role of big data text analytics as a means to enhance the effectiveness of KM. The paper provides important insights that can be applied to different business functions, from supply chain management to marketing management to support KM, through the use of big data text analytics.Originality/valueThe study demonstrates the practical application of the big data tools for data visualisation, and, with it, improving KM.

Content Analysis of Mediated Associations: An Automated Text-Analytic Approach

ABSTRACTDue to the fact that mediated associations are a central aspect of many mass communication theories, their measurement is of central interest for communication research. Mediated associations are defined as the repeated pairing of an object (e.g., social group, political party) with specific attributes (e.g., crime, economy). In this article, we introduce a recently developed, automated text-analytic technique. We present an application of this method in the media stereotyping domain via the content analysis of German news coverage of Islam. As predicted, the analysis revealed substantial mediated associations between Islam-related concepts and violence (e.g., “Koran + violence”), terror (e.g., “Islam + terror”), dehumanization (e.g., “Muslims + animal-related terms”), and general negativity (valence). We discuss the promises and pitfalls of this method, make software suggestions, and provide application-related information for speedy dissemination in communication research.

A Text Analytic Approach to Classifying Document Types

Background: While it is commonly recognized that almost every work and research discipline utilize their own taxonomy, the language used within a specific discipline may also vary depending on numerous factors, including the desired effect of the information being communicated and the intended audience. Different audiences are reached through publication of information, including research results, in different types of publication outlets such as newspapers, newsletters, magazines, websites, and journals. Prior research has shown that students, both undergraduate and graduate, as well as faculty may have a difficult time locating information in different publication outlet types (e.g., magazines, newspapers, journals). The type of publication may affect the ease of understanding and also the confidence placed in the acquired information. A text analytics tool for classifying the source of research as a newsletter (used as a substitute for newspaper articles), a magazine, or an academic journal article has been developed to assist students, faculty, and researchers in identifying the likely source type of information and classifying their own writings with respect to these possible publication outlet types. Literature Review: Literature on information literacy is discussed as this forms the motivation for the reported research. Additionally, prior research on using text mining and text analytics is examined to better understand the methodology employed, including a review of the original Scale of Theoretical and Applied Research system, adapted for the current research. Research Questions: The primary research question is: Can a text mining and text analytics approach accurately determine the most probable publication source type with respect to being from a newsletter, magazine, or journal? Methodology: A text mining and text analytics algorithm, STAR’ (System for Text Analytics-based Ranking), was developed from a previously researched text mining tool, STAR (Scale of Theoretical and Applied Research), that was used to classify the research type of articles between theoretical and applied research. The new text mining method, STAR’, analyzes the language used in manuscripts to determine the type of publication. This method first mines all words from corresponding publication source types to determine a keyword corpus. The corpus is then used in a text analytics process to classify full newsletters, magazine articles, and journal articles with respect to their publication source. All newsletters, magazine articles, and journal articles are from the library and information sciences (LIS) domain. Results: The STAR’ text analytics method was evaluated as a proof of concept on a specific LIS organizational newsletter, as well as articles from a single LIS magazine and a single LIS journal. STAR’ was able to classify the newsletters, magazine articles, and journal articles with 100% accuracy. Random samples from another similar LIS newsletter and a different LIS journal were also evaluated to examine the robustness of the STAR’ method in the initial proof of concept. Following the positive results of the proof of concept, additional journal, magazine, and newsletter articles were used to evaluate the generalizability of STAR’. The second-round results were very positive for differentiating journals and newsletters from other publication types, but revealed potential issues for distinguishing magazine articles from other types of publications. Discussion: STAR’ demonstrates that the language used for transferring information within a specific discipline does differ significantly depending on the intended recipients of the research knowledge. Further work is needed to examine language usage specific to magazine articles. Conclusions: The STAR’ method may be used by students and faculty to identify the likely source of research or discipline-specific information. This may improve trust in the reliability of information due to different levels of rigor applied to different types of publications. Additionally, the STAR’ classifications may be used by students, faculty, or researchers to determine the most appropriate type of outlet and correspondingly the most appropriate type of audience for the reported information in their own manuscripts, thereby improving the chance for successful sharing of information to appropriate audiences who will deem the information to be reliable, through publication in the most relevant outlet type.

Examining the Impact of Prime Minister Narendra Modi's Speeches on the Indian Stock Markets – A Text Analytics Approach

This paper examines the effect of Prime Minister Narendra Modi's speeches on the stock markets. A total of 63 selected speeches have been analysed starting from May 2014 up to July 2017. The speeches have been classified based on the type of effect that they would have on the markets as in positive, negative or no effect. The text of all the three categories of speeches has been analysed using text mining and analytics, and the differences in the speeches (words) have been identified. This study aims at adopting text mining as a method to predict market movements.

The determinants of online customer ratings: a combined domain ontology and topic text analytics approach

Merchants, as well as customers, have noticed the importance of online product reviews and numeric ratings in electronic commerce websites. It is valuable if merchants can discover some potential customer value from the sheer volume of data. This paper contributes a semantic text analytics approach that can dig out the customers' most basic concerns about their online purchase choices. More specifically, based on the hypothesis that the product reviews and overall ratings estimated by same person in a tiny time interval have a great relevance, we dexterously utilize this relevance to realize the embedded customer value. In the proposed method, take the single lens reflex camera for example, an innovative aspect extraction method that comprehensively considers the product ontology and results of the topic modeling method latent Dirichlet allocation is applied. As a result, 8 specific aspects are identified from the experimental results. For each aspect, a self-contained review feature corpus is created as an extension of some seed terms. After aspect-based sentence segmentation and context-sensitive sentiments preprocessing, aspect-oriented sentiment analysis is applied. Multiple regression analysis is then used as a statistical measure to discover determinant aspects of overall ratings. The results reveal that cost performance, image quality and product integrity are the three most influential aspects. The practical implication of our research is that merchants can efficiently modify their products, to satisfy more customers and also boost sales performance.

The determinants of crowdfunding success: A semantic text analytics approach

In the era of the Social Web, crowdfunding has become an increasingly more important channel for entrepreneurs to raise funds from the crowd to support their startup projects. Previous studies examined various factors such as project goals, project durations, and categories of projects that might influence the outcomes of the fund raising campaigns. However, textual information of projects has rarely been studied for analyzing crowdfunding successes. The main contribution of our research work is the design of a novel text analytics-based framework that can extract latent semantics from the textual descriptions of projects to predict the fund raising outcomes of these projects. More specifically, we develop the Domain-Constraint Latent Dirichlet Allocation (DC-LDA) topic model for effective extraction of topical features from texts. Based on two real-world crowdfunding datasets, our experimental results reveal that the proposed framework outperforms a classical LDA-based method in predicting fund raising success by an average of 11% in terms of F1 score. The managerial implication of our research is that entrepreneurs can apply the proposed methodology to identify the most influential topical features embedded in project descriptions, and hence to better promote their projects and improving the chance of raising sufficient funds for their projects.

Predicting box office from the screenplay: A text analytical approach

Abstract Empirical studies of the determinants of box office revenues have mostly focused on post-production factors – that is, ones known after the film has been completed and/or released. Relatively few studies have considered pre-production factors – that is, ones known before a decision has been made to green-light a film project. The current study directly addresses this gap in the literature. Specifically, we develop and test a relatively parsimonious, pre-production model to predict the opening weekend box office of 170 US-produced, English-language feature films released in the years 2010 and 2011. Chief among the pre-production factors we consider are those derived from the textual and content analysis of the screenplays of these films. The most important of these is determined through the application of network text analysis (NTA) – a method for rendering a text as a map or network of interconnected concepts. As predicted, we find that the size of the main component of a screenplay’s text network strongly predicts the completed film’s opening weekend box office.

Perceptual mapping of hotel brands using online reviews: a text analytics approach

Product perceptual mapping in the lodging industry has largely relied on survey and focus group methods to represent consumer perceptions of how the hotel product compares to one another. The more recent availability of online reviews represents a potentially powerful source of data that can be used to provide insights into how brands are perceived. This study uses a text analysis approach to create perceptual maps from the most frequent terms used in a data set collected from an online travel agency. These maps show not only the ability for text analytics to produce insights on brands, but also their potential for understanding how brands are able to be differentiated in the minds of consumers. The findings indicate that consumers perceive brands to be positioned similar to the structure defined by the industry. Brands were shown to be associated with terms indicative of the class of hotel that formed the majority of the brand. This suggests that online consumer reviews can be used to represent the level of differentiation between hotel brands and thus, are a useful source for understanding the market structure of the hotel industry. Implications for both research and practice are also discussed.

Mapping discursive dynamics of the financial crisis: a structural perspective of concept roles in semantic networks

Convenient access to vast and untapped collections of documents generated by organizations is a highly valuable resource for research. These documents (e.g., press releases) are a window into organizational strategies, communication patterns, and organizational behavior. However, the analysis of large document corpora requires appropriate automated methods for text mining and analysis that are able to take into account the redundant and predictable nature of formalized discourse. We use a combination of semantic network analysis and network centrality measures to overcome these particular challenges and to explore the dynamic structural space of concepts in formalized documents pertaining to the recent financial crisis. For our analyses, we collect the press releases of the European Central Bank (ECB) and the United States’ Federal Reserve System (Fed) issued between 2006 and 2013 in order to examine their semantic networks before, during, and after the recent financial crisis. Their press releases are notably impactful in their influence on other financial institutions and society at large, especially during times of financial volatility. The structural space created from joint centrality metrics reveals salient shifts in the discursive practices of the ECB and Fed. In particular, the Fed exhibits greater attentiveness to the financial crisis especially during the crisis itself, while the ECB’s attention is delayed and increasing steadily. Furthermore, we show both the Fed’s and the ECB’s discourse transitioning into a new “hybrid” state, rather than returning to the pre-crisis status quo. Examining the semantic networks of organizational text documents, we find that our analytic approach reveals important discursive shifts, which would not have been discovered under traditional text-analytic approaches. We demonstrate the utility of this approach in investigating large text corpora of organizational discourse, and we anticipate our methods to be comparably valuable in the analysis of a large spectrum of formal and informal discourse.

What can big data and text analytics tell us about hotel guest experience and satisfaction?

The tremendous growth of social media and consumer-generated content on the Internet has inspired the development of the so-called big data analytics to understand and solve real-life problems. However, while a handful of studies have employed new data sources to tackle important research problems in hospitality, there has not been a systematic application of big data analytic techniques in these studies. This study aims to explore and demonstrate the utility of big data analytics to better understand important hospitality issues, namely the relationship between hotel guest experience and satisfaction. Specifically, this study applies a text analytical approach to a large quantity of consumer reviews extracted from Expedia.com to deconstruct hotel guest experience and examine its association with satisfaction ratings. The findings reveal several dimensions of guest experience that carried varying weights and, more importantly, have novel, meaningful semantic compositions. The association between guest experience and satisfaction appears strong, suggesting that these two domains of consumer behavior are inherently connected. This study reveals that big data analytics can generate new insights into variables that have been extensively studied in existing hospitality literature. In addition, implications for theory and practice as well as directions for future research are discussed.

The Bonding of a Band and a Brand: On Music Placement in Television Commercials from a Text Analytical Perspective

This article presents a four-part text analytical approach to the examination of music placement in television commercials. The approach is developed through a case analysis of a commercial for Apple's iPad featuring the song “There Goes My Love” by the Blue Van. The analysis illustrates how a seemingly “happy marriage” between a band and a brand can be characterized by a power imbalance that arguably manifests at the level of text structure.

Er fagbøger en del af børnelitteraturen?

Is non-fiction also a part of children’s literature? In recent decades, children’s literature researchers have only considered fi ction children’s literature (Maria Nikolajeva 1998 and Torben Weinreich 2004), and certain younger researchers have shown a tendency to write about experimental books by prize-winning authors (Bodil Kampp 2002). Very few researchers have shown an interest in non-fi ction for children, and the consequence is that a great many publications for children have been overlooked. In the Nordic countries, Nina Goga’s doctoral thesis from 2008 is the only exception from this exclusive defi nition of children’s literature. In this article, I present a defi nition of children’s literature that includes non-fi ction. In this defi nition, literature means 'something written’ after 'litera’ (Latin: letter). The purposes of the article are, on the one hand, to discuss different defi nitions and characteristics of non-fi ction for children, and on the other hand to identify ways to analyze these books as literature for children. The article includes a discussion of a series of books about zoology by the Danish author Bent Jorgensen and the illustrator Birde Poulsen. One book in particular is discussed as an example of contemporary non-fiction and that is Om natten (In the Night, 2005). This book is subjected to analytical tools from literature studies, and one of the points is that non-fi ction should be interpreted and described through a textanalytical approach. Keywords: defi nitions of children’s literature, children’s literature research, non-fi ction for children, analysis of children’s literature. (Published: 3 March 2011) Citation: Nordic Journal of ChildLit Aesthetics, Vol. 2 , 2011 DOI: 10.3402/ blft.v2i0.5836 Note: This article is being published simultaneously in Barnboken – tidskrift for barnlitteraturforskning/Journal of Children’s Literature Research and Nordic ChildLit Aesthetics/Barnelitteraert forskningstidsskrift

Formulation and realisation of evaluation policy: inconcistencies and problematic issues

The introduction of the national evaluation system in the Norwegian education system can be described as a shift in the Norwegian educational policy from the use of input oriented policy instruments towards a more output oriented policy. The new tool-kit consists of different evaluation tools, such as standardised tests, diagonistic tests etc. which create new expectations to schools and principals. On the one hand, this article focuses on the policy purposes of the evaluation tools as they are formulated in policy documents. On the other hand, it investigates principals’ perceptions of the use of the evaluation tools to improve student achievements. A text analytic approach focusing on language and discourse is used to analyse policy documents. The analysis of the principals’ perceptions is based on a quantitative analysis of survey data and Structural Equation Modeling is applied as an analytic technique. Based on the analysis, questions can be raised whether all the policy purposes can be fulfilled or whether the tools might produce other effects than the objectives assigned to them. Problematic aspects related to the tools’ modes of regulations and thereby the choice of tools are discussed, as well as inconsistencies between the policy purposes and the use of tools in practice.

Food product development

PurposeThis paper aims to illustrate a new method to cluster consumer attribute preferences and to transform spontaneously written texts by consumers about a certain favourite food product (hamburger) into distinct preference clusters of attributes.Design/methodology/approachA new way of finding significant clusters of consumer attribute preferences is developed by means of a new text analytical approach (Pertex) and a multi‐step two‐sided cluster analysis procedure.FindingsClear linkages were ascertained between four respondent and four preference clusters for the two key product dimensions taste and ingredients of the hamburger.Research limitations/implicationsClusters expressed were in close conformity to the conception of the standard hamburger. Only one student sample (N=100) was used.Practical implicationsA new and practical method to transform written text into distinct consumer preferences (segments) was tested using a multi‐step cluster analysis to support food innovation in the food industry.Originality/valueProduct dimensions were integrated in a meaningful way into distinct preference clusters that could be used to segment consumers when innovating new food products.

Discovery of protein-protein interactions using a combination of linguistic, statistical and graphical information

BackgroundThe rapid publication of important research in the biomedical literature makes it increasingly difficult for researchers to keep current with significant work in their area of interest.ResultsThis paper reports a scalable method for the discovery of protein-protein interactions in Medline abstracts, using a combination of text analytics, statistical and graphical analysis, and a set of easily implemented rules. Applying these techniques to 12,300 abstracts, a precision of 0.61 and a recall of 0.97 were obtained, (f = 0.74) and when allowing for two-hop and three-hop relations discovered by graphical analysis, the precision was 0.74 (f = 0.83).ConclusionThis combination of linguistic and statistical approaches appears to provide the highest precision and recall thus far reported in detecting protein-protein relations using text analytic approaches.