Text Analysis Tools Research Articles

Analyzing how the sobek tool can assist students’ writing

Reading and text production are two important skills for everyone, but it is known that even students in higher education have difficulties how to write high-quality texts. Currently, there are several automatic text analysis tools, also well-known as text mining tools, available on the Internet (paid and free) which can be used to support text production, such as LanguageTool (Zhang et al., 2018), TextAlyser (TextAlyser, 2019), TagCrowd (TagCrowd, 2019), and Sobek (Macedo et al., 2016). These tools usually highlight attention points in a text, present a statistical analysis, suggest connection words, and emphasize locals with repetitive words, turning out a text with higher quality. Thus, this paper presents a case study using the Sobek automatic text analysis tool to investigate its potential to support students in the learning process (reading and production/writing). One group of 26 students enrolled in 9th grade from a middle school in the Paraiba state, Brazil, participated in writing activities using the Sobek tool. From the experiments, the results have shown an upgrade in text writing skills, especially showing a vocabulary more diversified and text structures, which are discussed in this paper.

Statistical clustering of documents via stochastic blockmodels

ABSTRACT As the online market grows rapidly, people are relying more on product review when they purchase the product. Hence, many companies and researchers are interested in analyzing product review which essentially a text data. In the current literature, it is common to use only text analysis tools to analyze text dataset. But in our work, we propose a method that utilizes both text analysis method such as topic modeling and statistical network model to build network among individuals and find interesting communities. We introduce a promising framework that incorporates topic modeling technique to define the edges among the individuals and form a network and uses stochastic blockmodels (SBM) to find the communities. The power of our proposed method is demonstrated in real-world application to Amazon product review dataset.

Using ChatGPT for human-computer interaction research: a primer.

ChatGPT could serve as a tool for text analysis within the field of Human-Computer Interaction, though its validity requires investigation. This study applied ChatGPT to: (1) textbox questionnaire responses on nine augmented-reality interfaces, (2) interview data from participants who experienced these interfaces in a virtual simulator, and (3) transcribed think-aloud data of participants who viewed a real painting and its replica. Using a hierarchical approach, ChatGPT produced scores or summaries of text batches, which were then aggregated. Results showed that (1) ChatGPT generated sentiment scores of the interfaces that correlated extremely strongly (r > 0.99) with human rating scale outcomes and with a rule-based sentiment analysis method (criterion validity). Additionally, (2) by inputting automatically transcribed interviews to ChatGPT, it provided meaningful meta-summaries of the qualities of the interfaces (face validity). One meta-summary analysed in depth was found to have substantial but imperfect overlap with a content analysis conducted by an independent researcher (criterion validity). Finally, (3) ChatGPT's summary of the think-aloud data highlighted subtle differences between the real painting and the replica (face validity), a distinction corresponding with a keyword analysis (criterion validity). In conclusion, our research indicates that, with appropriate precautions, ChatGPT can be used as a valid tool for analysing text data.

Mind the Gap: Gender Disparity in Online Learning Platform Interactions

Problem definition: Education technology innovations, such as massive open online course (MOOC) platforms, could potentially enable a more inclusive learning environment by delivering education to traditionally disadvantaged learners, like women. However, inclusivity does not necessarily translate into equal treatment on the platform. We investigate whether female and male learners benefit equally from forum discussions—typically the only form of interaction available—in online learning platforms. Methodology/results: Utilizing a large-scale, interaction-level data set on 174 courses on Coursera, we uncover an economically sizable and statistically significant disparity between male and female learners in receiving responses to their posts in MOOC discussion forums. On average, female learners’ questions are 3.11 percentage points less likely to receive responses from teaching staff than male learners’ questions, which equals 15.2% of the female group average. We also find significant gender disparity in staff response quality and sentiments. We investigate possible mechanisms behind the gender disparity using new techniques, including textual analysis tools. We show that the disparity is not because of content differences in male and female learners’ posts, nor is it attributable to their linguistic styles or the reputation of the posters. Instead, our results are most consistent with a male-driven gender homophily mechanism; although female staff members are gender neutral in their interactions with learners, male staff members systemically prefer responding to posts from male learners. We additionally show that receiving staff response leads to significant improvement in course passing rates, particularly for female learners. Therefore, the unequal access to information through course forums unfavorably hinders female learners’ performance. Managerial implications: Our results provide operational and organizational suggestions to platforms and content providers, including degendering user identifiers, implementing a content-focused post recommendation system, incorporating a gender-neutral user reputation system, promoting the recruiting of female teaching staff, and providing staff training that highlights the importance of gender-neutral interactions. Supplemental Material: The online appendix is available at https://doi.org/10.1287/msom.2022.0426 .

The interactive Leipzig Corpus Miner: An extensible and adaptable text analysis tool for content analysis

We present the interactive Leipzig Corpus Miner (iLCM), which is the result of the development of an integrated research environment for the analysis of text data. The key features of iLCM compared to existing software tools for computer-assisted text analysis are its flexibility and scalability. The tool includes functions to offer commonly needed methods for automatic processing of text, such as preprocessing, standard text analysis, and visualization, which would be very time consuming without a ready-to-use software tool. To also provide more methodological flexibility, the iLCM is not tied to one specific class of research question, but can easily be extended to other applications. In this article, we will focus on the capabilities and the aspects of adaptability, extensibility, and data exchange with other tools from the field of empirical content analysis. We will present the features of the iLCM and showcase individual examples and a case study that demonstrates the practical use of the tool.

Are we There yet? Thematic Analysis, NLP, and Machine Learning for Research

Thematic analysis is a well-established technique for qualitative analysis which is covered in traditional research methods training. The objective of thematic analysis is to elicit themes and significant topics from discursive data such as free style discussions and semi structured or unstructured interviews or comments. The approach is laborious and time consuming and requires a significant input from researchers for identifying and coding the themes although software tools such as NVivo, T-Lab and IRaMuTeQ can aid with results presentation. Recent developments in Machine Learning (ML) and Natural Language Processing (NLP) have boosted interest in text analytics and its applications to social science research. For example, automatic topic identification using ML NLP offers valuable insights in social media analytics. However, machine learning techniques conventionally rely on large data sets to enable the algorithm to elicit themes. More recent research efforts have turned to the performance of machine learning approaches with smaller data sets. This study aims to compare and contrast the effectiveness of Machine Learning NLP vs human generated themes using the text analytics tools NVivo, T-Lab, IRaMuTeQ, as well as the low-code ML tool KNIME for automatically eliciting themes from academic literature review in the contexts of service operations management research and semi-structured customer interviews. Results indicate that the ML NLP approach has the potential to automatically detect research themes even with small data sets, although the results vary across the different tools and are dependent on the capabilities of the built-in text analytic algorithms. In particular, T-Lab offered the best mapping of machine learning derived topics to researcher themes, and KNIME proved the most robust software, able to derive meaningful topics even with very small sample sizes. The implications for training research students are also significant as they suggest that the inclusion of ML NLP tools and algorithms in the training curriculum of social scientists may be beneficial.

A method for analyzing text using VOSviewer

The need for technical support for data handling and visualization solutions has increased in tandem with the complexity of today's data and information, that is of multiple sources, huge in size and of different formats. This study focuses on handling and analyzing text-based data. Despite many available text analysis tools, there is a high demand among researchers for easy- to-use tools yet scalable and with incomparable visualization features. Of recent, there has been a significant focus on utilizing VOSviewer, an open-source software for bibliometric analysis. This software is able to analyze a significant amount of data and provide excellent network data mapping. However, there is a lack of existing work in evaluating this sophisticated tool for text analysis. Thus, this article explores the capability of VOSviewer and presents evidence-based implementation of this software for text analysis.Specifically, this study demonstrates the usage of VOSviewer to analyze text based on YouTube interviews related to ChatGPT. Hence, this study significantly contributes by processing textual data and producing visualization network maps that are different from bibliometric data. The study recognizes VOSviewer as a powerful tool for data visualization in mapping text data and illustrates the potential of this software for analyzing text networks in various fields.•The study illustrates how text analysis and visualization can be realized using VOSviewer, an open-source software mostly used for biblio- metric analysis.•The study presents the workflow indicating how the dataset can be prepared as input for VOSviewer for text analysis.•The study proves that VOSviewer is a powerful tool for data visualization and network mapping for any type of network data including transcripts from social media.

Comparing Textual Analysis Tools To Classify Sustainability Information In Corporate Reporting

Comparing Textual Analysis Tools To Classify Sustainability Information In Corporate Reporting

Investigating the aftermath of the Türkiye 2023 earthquake: exploring post-disaster uncertainty among Syrian migrants using social network analysis with public health approach.

On February 6th, 2023, a doublet earthquake struck Türkiye, impacting more than 15 million people including migrants, and resulting in over 50,000 deaths. The Syrian migrants experience multiple uncertainties in their daily lives which are further compounded by multifaceted challenges of the post-disaster environment. Social media was used intensively and with impunity in this environment and thereby provides a window into the explicit and implicit dynamics of daily life after a disaster. We aimed to explore how a post-disaster environment potentially generates new uncertainties or exacerbating pre-existing ones for migrants through social media analysis with an indirect perspective, in the context of 2023-Earthquake in Türkiye and Syrian migrants. Social network analysis was used to analyze Twitter-data with the hashtags 'Syrian' and 'earthquake' during a 10-day period beginning on March 22nd, 2023. We calculated network metrics, including degree-values and betweenness-centrality and clustered the network to understand groups. We analyzed a combination of 27 tweets with summative content analysis using a text analysis tool, to identify the most frequently used words. We identified the main points of each tweet and assessed these as possible contributors to post-disaster uncertainty among migrants by using inductive reasoning. There were 1918 Twitter users, 274 tweets, 124 replies and 1726 mentions. Discussions about Syrian migrants and earthquakes were established across various groups (ngroups(edges > 15) = 16). Certain users had a greater influence on the overall network. The nine most frequently used words were included under uncertainty-related category (nmost_frequently_used_words = 20); 'aid, vote, house, citizen, Afghan, illegal, children, border, and leave'. Nine main points were identified as possible post-disaster uncertainties among migrants. The post-disaster environment has the potential to exacerbate existing uncertainties, such as being an undocumented migrant, concerns about deportation and housing, being or having a child, inequality of rights between being a citizen and non-citizen, being in minority within minority, political climate of the host nation and access to education or to generate new ones such equitable distribution of aid, which can lead to poor health outcomes. Recognizing the possible post-disaster uncertainties among migrants and addressing probable underlying factors might help to build more resilient and healthy communities.

A Multi Document Summarization of Learning Materials using Bigram Embedding Technique and Integer Linear Programming

In the present era of the Internet, teachers and learners are heavily inclined to use e-learning systems for an efficient learning process. Due to the proliferation of educational text contents in these e-learning systems, the need for incorporating advanced text analysis tools and techniques are becoming inevitable. Multi Document Summarization (MDS) is a technique for producing concise summaries from a collection of related text documents. The usage of MDS in the context of e-learning is more promising for providing summaries for learning materials which helps students and teachers to focus on key concepts of the learning materials. In this paper a semantic approach towards the learning material summarization is proposed based on bigram embedding and ILP technique. This approach considers bigram as the basic meaningful semantic unit of the sentences to understand and summarize documents. Embedding techniques are employed to learn the vector representation of phrases to semantically identify similar phrases to reduce the redundancy and improving coherence. Using ILP technique, the summaries were generated by selecting important sentences while reducing the redundancy using phrase vectors. Experimental results on newly created educational dataset (EduSumm) shows better performance compared to the baseline systems.

THE AESTHETICS OF POSTMODERNISM: A CRITICAL REVIEW

This study extrapolates the aesthetics of postmodernism as a theoretical category. In this connection, the study briefly examines the problematics of definition associated with the concept essentially because of its ambivalent nature and paradoxical nexus with its root precursor, modernism. The study then distils some of the main features and purviews of postmodernism by major theorists like Jean-FracoisLyotard and Jean Baudrillard, as well as some key arguments in connection with the concept by scholars like Frederick Jameson, Terry Eagleton, Christopher Norris, Alan Sokal, and Jean Bricmont. The study posits that such contestations on the concept is show that it is a worthy site for intellectual engagements and a viable tool for textual interpretation and analysis.

Coh-Metrix 시스템을 활용한 고등학교 영어 모의고사 읽기 지문의 학년 간 연계성 분석

The main objective of this study was to analyze the continuity of reading passages in high school English mock College Scholastic Ability Test (CAST) exams using Coh-Metrix, a multi-level text analysis tool. To achieve this, the study constructed a corpus of reading passages from the 2022 high school English mock exams and subjected them to a broad range of Coh-Metrix measures. These measures included basic measures (the number of words, the number of sentences, average word length, average sentence length), word frequencies (word frequencies for content words), word features (imageability, concreteness, age of acquisition, familiarity), lexical diversity measures (type-token ratios for content words), personal pronouns (first person pronouns, second person pronouns, third person pronouns), connectives, readability indices (Flesch Reading Ease, Flesch-Kincaid Grade Level), syntactic complexity (noun density scores, the number of words before main verbs), coreference cohesion measures, and semantic cohesion measures. The main results revealed that the continuity of high school English mock tests was well established for average word and sentence length measures, the average number of words, word frequencies, word familiarity, second person pronouns, standard readability indices, and syntactic complexity measures. These findings have implications for the development of reading passages in high school English mock exams.

Threat Conceptions in Global Security Discourse: Analyzing the Speech Records of the United Nations Security Council, 1990–2019

Abstract Since the end of the Cold War, the notion of global security, and presumed threats to it, has undergone considerable expansion and diversification. This process has been led by the United Nations Security Council (UNSC), where active deliberations concerning “threat(s) to the peace” have taken place among major international actors. Despite a sizable accumulation of scholarly arguments, however, the defining features of the structure and dynamics of the post-Cold War security discourse remain ambiguous. To address these ambiguities, this study investigates the entire body of Council deliberations over the past three decades. Based on an original dataset consisting of policy statements delivered at the UNSC, the study employs quantitative text analysis tools, including word embedding, to examine how council members have conceived the notion of security threat in terms of the various issues and entities discussed. It shows the security discourse at the UNSC to be highly stratified and reveals the persistent and pervasive influence of terrorism and the proliferation of weapons of mass destruction, which constitute the limited common grounds shared by the Council’s permanent members. These findings caution against the unconstrained use of certain theoretical constructs widely employed in other works, most notably, “securitization” and “interpretative community.”

A new approach to recognizing the use of attitude markers by authors of academic journal articles

This study investigates the use of Attitude Markers(AMs) by native academic authors of English (NAAEs) and Turkish-speaking academic authors of English (TAAEs) in 100 academic articles on Teacher Education. The primary objectives are to examine the forms and functions of AMs used by both groups to indicate their stance in articles and to compare the frequency and variety of AMs used by each group. The study employs a corpus-based approach and adopts a graph visualization method to present the findings. The data were cleaned using a software-supported approach to improve the efficiency of corpus compilation. The data were analyzed using the Antconc text analysis tool (Anthony, 2011) and Log-likelihood statistics. The reliability of the analysis was tested by calculating the inter-rater reliability. To do this, the content coded by one of the researchers and an independent rater was compared using Cohen’s Kappa coefficient. The results ranged from 0.81 to 0.92, indicating a high level of reliability. Later, the findings were visualized using a radial knowledge graph. The statistical analysis showed significant differences in the use of certain AMs between the two groups, including AMs related to “assessment” (-13,20 LL; p<.01) and “significance” (-82,64 LL; p<.01). The findings indicate that both NAAEs and TAAEs commonly use AMs to convey their stance, with ‘significance’ and ‘assessment’ being the most frequent functional categories, and ‘adjective’ being the most commonly used form of AMs in both corpora. The findings provide valuable insights into the use of AMs in academic writing and can inform the development of English for academic purposes (EAP) course materials to enhance the academic writing skills of novice writers. The results of the study suggest that future research could use graph visualization to carry our corpus studies and could explore the effectiveness of using Artificial Intelligence (AI) technologies to minimize human bias in qualitative analyses.

Using SFL-based text analysis to inform instruction for emergent bilingual learners

Emergent Bilingual Learners (EBs) need language-focused instructional support if they are to access content, make meaning, and engage critically with academic texts in English. Text analysis informed by systemic functional linguistics (SFL) helps teachers identify “the language of schooling” (Schleppegrell, 2004) which they will need to make visible to their students. The authors, both teacher educators in an ESOL endorsement program, recognize that both the teacher candidates who are analyzing texts and the students whose instruction will be informed by the analysis engage in literacy practices that may not be recognized and valued by all teachers or aligned with the language demands of mandatory, high-stakes assessments. With that in mind, we envision a text analysis assignment that promotes language as meaning based, rather than rule based, and additive, rather than subtractive (Garcia, 2009) in terms of the language resources of teachers and students in language learning settings. Additionally, we look for ways to support our teacher candidates in interrogating texts critically as part of their analysis to uncover dominant perspectives. This practice-based article models the process of SFL-based text analysis facilitated by a text analysis tool we designed. The goal is that teachers can apply what they have learned from their analysis to create language-focused instruction that both supports academic language learning and promotes critical stances towards the connections between language choices and meaning making in specific academic contexts/disciplines. Additionally, we encourage teachers to use a variation of this text analysis format with students to explore how language is used in the text to develop all languages in the students' linguistic repertoire.

On Dissonance and Late Style: Spenser with Theodor W. Adorno

This essay makes a case for a reassessment of The Faerie Queene in light of Adorno’s philosophical thinking about dissonance. Focusing on Book II, I analyze Spenser’s productive use of dissonant elements at the different levels of narrative and style, which produce a similar effect to the alienating techniques that Adorno praises in literary and musical forms of expression. I then consider Adorno’s discussion of dissonance as an essential aspect of late style and bring it to bear on Spenser’s poetic practice in the conclusive Mutabilitie Cantos of the epic. I suggest that this comparative analysis may not only open up new avenues for interpreting Spenser’s epic but also help us to reassess the significance of Adorno’s more neglected discussions of dissonance in his minor works of literary criticism, which gesture toward the importance of this concept as a tool for textual analysis.

Delicious angst and tooth-rotting fluff: Distant reading community discourses of emotion in Harry Potter fanfiction comments

This article employs distant reading to examine discursive norms for expressing emotion in comments on Harry Potter fanfiction on Archive of Our Own (AO3). Using text analysis tools to identify collocational patterns, the article shows how fanfiction engages this community and how community members express their engagement in accordance with community discourses. The analysis transcends the level of individual utterances by examining large-scale patterns in the data. Comparing comments for three fanfiction genres (angst, fluff and hurt/comfort) reveals three patterns. First, commenters frequently describe stories about suffering in positive terms. Second, metaphors likening fanfiction consumption to food consumption are prevalent in all genres. Commenters also use language blending physical and emotional sensations. Finally, commenters describe stories about positive emotions using negative metaphors of rot, decay, gluttony or overload. This use of positive or negative language need not indicate positive or negative judgements but instead reveals discursive fields to which fanfiction reading is linked. Additionally, comments indicate that fanfiction is used to influence emotional states. These findings contribute to an understanding of the impact of fanfiction within its community and raise questions regarding the role of emotion in fanfiction reading.

Identifying trends in information security and privacy concern research

Text mining is a research method that can be used to detect research trends and developments in various fields. In this study, an automated textual analysis tool (Voyant Tools) is applied to a vast corpus of academic papers to identify research trends in the fields of information security and privacy concern, focusing on the differences between the first two decades of the twenty-first century. Furthermore, the conceptual proximity between the related terms ‘information security’ and ‘privacy concern’ is investigated by identifying textual trends. We discovered that, while the first decade of information security research was not entirely defined, the second decade focused on privacy-related issues. The focus of privacy concern research was on commerce and marketing in the first decade and on the social dimension in the second decade. This study supports the use of textual analysis of academic literature to identify research trends in various fields, including technological fields.

Informational vs. emotional B2B firm-generated-content on social media engagement: Computerized visual and textual content analysis

While social media marketing plays an increasingly significant role in the B2B context, there is still limited research examining how to increase B2B social media engagement. The need for more research is becoming more pressing given the recent shift in social media content from text-centric to image-oriented experience. Building on the elaboration likelihood model and employing computerized visual and textual analysis tools, the present research investigates how informational and emotional cues in B2B social media content influence viewer engagement. By analyzing 5362 single-image posts from the Instagram accounts of 10 B2B companies across five industries, this research demonstrates that informational cues are more effective than emotional cues in driving viewer engagement, and that informational cues are even more effective when presented in visual content, as compared to textual content. The findings of this research contribute to the literature on B2B social media literature and offer managerial implications for B2B social media marketing.

Lay representations of artificial intelligence and autonomous military machines.

This study is about how lay persons perceive and represent artificial intelligence in general as well as its use in weaponised autonomous ground vehicles in the military context. We analysed the discourse of six focus groups in Estonia, using an automatic text analysis tool and complemented the results by a qualitative thematic content analysis. The findings show that representations of artificial intelligence-driven machines are anchored in the image of man. A cluster analysis revealed five dominant themes: artificial intelligence as programmed machines, artificial intelligence and the problem of control, artificial intelligence and its relation to human life, artificial intelligence used in wars and ethical problems in developing autonomous weaponised machines. The findings are discussed with regard to people's tendency to anthropomorphise robots despite their lack of emotions, which can be seen as a last resort when confronting an autonomous machine where the usual interpersonal understanding of intentions does not apply.