Authorship Attribution Research Articles

AI as a Co-Author? We Should Also Ask Philosophical (and Ethical) Questions

Dear Editors With great interest and attention, I read authors’ short but stimulating editorial articles, which also contain extremely valuable questions [1]. The questions posed by the authors and the emphasis on referred articles reflecting different perspectives seem to reflect content about the practical benefits, risks, and inevitability of the use of technology. In addition, it is seen that the valuable comments on the article focus on issues such as the risk of harm and publication ethics issues in academic use of AI [2,3]. Considering the discourse of the article’s authors, which invites discussion, it is seen that questions that go beyond mere responsibility or practical benefits or risks should also be asked. In this context, I think that questions based on philosophical and ethical foundations should also be asked. For example, What is AI’s ontological position as a writer is a very fundamental question. That is, does AI reflect a “particular” individual/entity as “a writer”, or does it reflect cognitive domination that has the power to access and process the knowledge of entire humanity easily, or does AI reflect a collective mind or "universal" as a product of the knowledge and cognitive history of humanity as a whole? I think these questions are notable for AI’s position as an author and whether that position is acceptable. Again, should AI be considered a tool (is given instrumental purpose) or as a value in itself (has intrinsic value)? As a fundamental question, this is also important for the acceptability or position of AI as an author. Without going into deep discussions for now, for example, how or what is the difference between AI as a tool and a classical data analysis tool? Does such a difference, if any, really warrant the attribution of authorship to AI? Questions like these seem important. Although different ethical discussions seem possible, the concept of responsibility to which the authors refer seems worth discussing. For example, it is also remarkable whether AI, as a responsible subject in itself, can also become a tool for other authors to avoid some responsibilities in research and publication ethics. It is known that such a debate exists in the field of clinical ethics [4]. As a result, as the article authors said, the authorship of artificial intelligence will lead to important discussions. Therefore, it will be necessary to consider philosophical (and ethical) questions about the position of artificial intelligence. Yours sincerely,

“Ulpianus scripsit”? Using Artificial Intelligence for authorship attribution of ancient Roman law texts

The present article seeks to demonstrate the usefulness of artificial intelligence for the exploration of the sources of Roman law. In a small experiment, a so-called support vector machine was employed to determine to which Roman jurist a given source text can be attributed. While the results were not perfect, they are sufficient to show the potential of new technologies for future research in the area.

Establishing a Health CASCADE-Curated Open-Access Database to Consolidate Knowledge About Co-Creation: Novel Artificial Intelligence-Assisted Methodology Based on Systematic Reviews.

Co-creation is an approach that aims to democratize research and bridge the gap between research and practice, but the potential fragmentation of knowledge about co-creation has hindered progress. A comprehensive database of published literature from multidisciplinary sources can address this fragmentation through the integration of diverse perspectives, identification and dissemination of best practices, and increase clarity about co-creation. However, two considerable challenges exist. First, there is uncertainty about co-creation terminology, making it difficult to identify relevant literature. Second, the exponential growth of scientific publications has led to an overwhelming amount of literature that surpasses the human capacity for a comprehensive review. These challenges hinder progress in co-creation research and underscore the need for a novel methodology to consolidate and investigate the literature. This study aimed to synthesize knowledge about co-creation across various fields through the development and application of an artificial intelligence (AI)-assisted selection process. The ultimate goal of this database was to provide stakeholders interested in co-creation with relevant literature. We created a novel methodology for establishing a curated database. To accommodate the variation in terminology, we used a broad definition of co-creation that encompassed the essence of existing definitions. To filter out irrelevant information, an AI-assisted selection process was used. In addition, we conducted bibliometric analyses and quality control procedures to assess content and accuracy. Overall, this approach allowed us to develop a robust and reliable database that serves as a valuable resource for stakeholders interested in co-creation. The final version of the database included 13,501 papers, which are indexed in Zenodo and accessible in an open-access downloadable format. The quality assessment revealed that 20.3% (140/688) of the database likely contained irrelevant material, whereas the methodology captured 91% (58/64) of the relevant literature. Participatory and variations of the term co-creation were the most frequent terms in the title and abstracts of included literature. The predominant source journals included health sciences, sustainability, environmental sciences, medical research, and health services research. This study produced a high-quality, open-access database about co-creation. The study demonstrates that it is possible to perform a systematic review selection process on a fragmented concept using human-AI collaboration. Our unified concept of co-creation includes the co-approaches (co-creation, co-design, and co-production), forms of participatory research, and user involvement. Our analysis of authorship, citations, and source landscape highlights the potential lack of collaboration among co-creation researchers and underscores the need for future investigation into the different research methodologies. The database provides a resource for relevant literature and can support rapid literature reviews about co-creation. It also offers clarity about the current co-creation landscape and helps to address barriers that researchers may face when seeking evidence about co-creation.

Rhythm-based authorship recognition in syllabic and accentual-syllabic verse

This contribution explores the extent to which rhythm-based features of poetic texts can contribute meaningfully to authorship recognition. We show that, although a binary categorization of languages as syllabic vs. accentual-syllabic fails to fully explain the differences. However, once we formalize accentual regularity as a continuum, our analysis shows that authorship attribution results improve as we move from the most to the least accentually regular languages. This result supports our hypothesis that accentual regularity is an inhibiting factor in authorship attribution as long as accentual regularity is understood as a continuous property.

Cracking double-blind review: Authorship attribution with deep learning.

Double-blind peer review is considered a pillar of academic research because it is perceived to ensure a fair, unbiased, and fact-centered scientific discussion. Yet, experienced researchers can often correctly guess from which research group an anonymous submission originates, biasing the peer-review process. In this work, we present a transformer-based, neural-network architecture that only uses the text content and the author names in the bibliography to attribute an anonymous manuscript to an author. To train and evaluate our method, we created the largest authorship-identification dataset to date. It leverages all research papers publicly available on arXiv amounting to over 2 million manuscripts. In arXiv-subsets with up to 2,000 different authors, our method achieves an unprecedented authorship attribution accuracy, where up to 73% of papers are attributed correctly. We present a scaling analysis to highlight the applicability of the proposed method to even larger datasets when sufficient compute capabilities are more widely available to the academic community. Furthermore, we analyze the attribution accuracy in settings where the goal is to identify all authors of an anonymous manuscript. Thanks to our method, we are not only able to predict the author of an anonymous work but we also provide empirical evidence of the key aspects that make a paper attributable. We have open-sourced the necessary tools to reproduce our experiments.

Evaluation of Feature Extraction Techniques in Automatic Authorship Attribution

Evaluation of Feature Extraction Techniques in Automatic Authorship Attribution

Attribution and Obfuscation of Neural Text Authorship: A Data Mining Perspective

Two interlocking research questions of growing interest and importance in privacy research are Authorship Attribution (AA) and Authorship Obfuscation (AO). Given an artifact, especially a text t in question, an AA solution aims to accurately attribute t to its true author out of many candidate authors while an AO solution aims to modify t to hide its true authorship. Traditionally, the notion of authorship and its accompanying privacy concern is only toward human authors. However, in recent years, due to the explosive advancements in Neural Text Generation (NTG) techniques in NLP, capable of synthesizing human-quality openended texts (so-called "neural texts"), one has to now consider authorships by humans, machines, or their combination. Due to the implications and potential threats of neural texts when used maliciously, it has become critical to understand the limitations of traditional AA/AO solutions and develop novel AA/AO solutions in dealing with neural texts. In this survey, therefore, we make a comprehensive review of recent literature on the attribution and obfuscation of neural text authorship from a Data Mining perspective, and share our view on their limitations and promising research directions.

Правила розвитку канонічно-правового світогляду

Pedagogy is not the same. The main reason for the contradictory, different contents of the science of pedagogy in the methodology, presentation of the material. The methodology of scientific and didactic thought depends in most cases on the worldview of the author. In spiritual pedagogy, the canonical-legal worldview dominates. This worldview forms pedagogy on an ontological and spiritual basis. The concept of worldview (worldview, worldview) is of German origin. In the Greek language you can find - cosmotheory. All attributions of authorship are caused by different interpretations - from an intuitive vision of the world to its interpretation [1, p. 347]. a worldview is not only an "overview" of the world, but something much bigger and more essential than that. A worldview is a certain image of the world, but also a certain projection of human experiences, aspirations, and expectations onto the world. At the same time, it is a certain effort, a certain mobilization of a person's internal resources, prompting and directing him to be involved in the world. According to the level of its organization, worldview can be divided into worldview, worldview, and worldview. World perception is a person's attitude to the world, world perception is an image of the world. And world understanding is a close combination of world explanation and world interpretation. Relates world perception, world perception and world understanding, world transformation [2, p. 76, 82-84]. In addition, the outlook should be organic. This means that everyone should consider and without any pressure to accept certain views on the world. No one has the right to impose his worldview by force [3, p. 22]. Organicity emphasizes the natural properties of views on the world and its assessment. Thoughts about nature and society in it are a regularity of a person. Man feels the need to feel the integrity of the universe and his place in it. Taking into account the above features of worldview, the following definitions exist in philosophy: worldview is a person's self-determination regarding his place in the world and his relationship with it [4, p. 569]; it is a set of developed generalized ideas, views, beliefs of a person about the world, himself, his place in the world and his purpose [4, p. 184-186] and others. Possessing such concepts about the worldview, we can start thinking about the canonical-legal worldview. Of course, it should be taken into account that there are different types of worldviews, among them apophatic, kataphatic, narrative, mythological, religious, philosophical, etc. We will pay special attention to the canonical legal worldview. The starting point will be that man is the image of God, which corresponds to the cataphatic (affirmative) worldview. You need to look at the world from the point of view of the preservation and development of nature, from the point of view of good (good), canonical law. It should be taken into account that man is the last in the creation of the world, therefore all the laws of the universe determine human meta-anthropology. Man, as the image of God, perceives the world by faith, feelings and reason without a special driving force, since this is his ontological status. Therefore, the following definition can be formulated: The canonical-legal worldview is the endowment by the Higher Powers of man of the natural and supernatural gift of intelligibly and sensibly realizing oneself in the image of God, who is subject to all the laws of creation of the world and life in it and responsibility for its harmony. That is, the empowerment to know and the responsibility for the illegality of this knowledge is the main requirement of the canonical-legal worldview. It goes without saying that human knowledge of the world has ontological limits. Let's consider the components of the canonical-legal worldview: the metaphysical gift of human perception of reality; man in the world as a projection of higher forces, the unity of the laws of the universe and human development, ontological laws of human life on earth, man's responsibility for the integrity of the universe. The metaphysical gift of human perception of reality is real. The special gift of knowing the world stems from the fact that a person is defined by ordological, existential and transcendental dimensions. The ordological dimension requires a natural mind from a person, i.e. intelligible principles that give him the opportunity to understand and organize his practical life, the gift of self-control, intelligent realization of the surrounding natural goods, a metaphysical understanding of nature gives grounds for asserting that a person ontologically perceives reality in the ordological dimension. The gift of reason, wisdom and especially intellectual sensitivity is needed here. These gifts of God are placed in every person, but not every person correctly develops his canonical-legal worldview on the basis of this.

A Transformer-Based Approach to Authorship Attribution in Classical Arabic Texts

Authorship attribution (AA) is a field of natural language processing that aims to attribute text to its author. Although the literature includes several studies on Arabic AA in general, applying AA to classical Arabic texts has not gained similar attention. This study focuses on investigating recent Arabic pretrained transformer-based models in a rarely studied domain with limited research contributions: the domain of Islamic law. We adopt an experimental approach to investigate AA. Because no dataset has been designed specifically for this task, we design and build our own dataset using Islamic law digital resources. We conduct several experiments on fine-tuning four Arabic pretrained transformer-based models: AraBERT, AraELECTRA, ARBERT, and MARBERT. Results of the experiments indicate that for the task of attributing a given text to its author, ARBERT and AraELECTRA outperform the other models with an accuracy of 96%. We conclude that pretrained transformer models, specifically ARBERT and AraELECTRA, fine-tuned using the Islamic legal dataset, show significant results in applying AA to Islamic legal texts.

String Kernel-Based Techniques for Native Language Identification

In recent years, Native Language Identification (NLI) has shown significant interest in computational linguistics. NLI uses an author’s speech or writing in a second language to figure out their native language. This may find applications in forensic linguistics, language teaching, second language acquisition, authorship attribution, identification of spam emails or phishing websites, etc. Conventional pairwise string comparison techniques are computationally expensive and time-consuming. This paper presents fast NLI techniques based on string kernels such as spectrum, presence bits, and intersection string kernels incorporating different learners such as a Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting-XGBoost (XGB). Feature sets for the proposed techniques are generated using different combinations of features such as n-word grams and noun phrases. Experimental analyses are carried out using 8235 English as a second language articles from 10 different linguistic backgrounds from a typical NLP benchmark dataset. The experimental results show that the proposed NLI technique incorporating a spectrum string kernel with an RF classifier outperformed existing character n-gram string kernels incorporating SVM, RF, and XGB classifiers. Also, comparable results were observed among different combinations of string kernels. Interestingly, the random forest classifier outperformed SVM and XGB classifiers with different feature sets. All the proposed NLI techniques demonstrated promising results with significant improvement in training time, with the best result attaining more than a 95 percent decrease in training time. The reduced training time of proposed techniques makes it well suited to scale NLI applications for production.

Bibliometric Analysis of Malaysian Authorship: Trends, Patterns, And Prospects

Bibliometric analysis has emerged as a crucial instrument for interdisciplinary scholars who aim to comprehend the complex terrain of scientific knowledge. The current study employed a bibliometric analysis to scrutinise bibliometric publications by Malaysian authors. The bibliometric datasets utilised in this study were collected from the Scopus and Web of Science (WoS) databases. The obtained datasets were subjected to analysis and visualisation through the utilisation of ScientoPy and VOSviewer. The results suggest that Malaysian authors have actively participated in producing bibliometric papers in both Web of Science (WoS) and Scopus databases. Ahmi A. from Universiti Utara Malaysia and Lim W.M. from the Swinburne University of Technology, Sarawak, have published 27 and 25 works, making them the most prolific authors. The terms “CiteSpace”, “artificial intelligence”, “PRISMA”, “machine learning”, “systematic literature review”, “Biblioshiny”, “Bibliographic coupling”, and “performance analysis” have garnered significant attention in academic circles in 2022. This study presented that India and the United Kingdom exhibit parity in co-author affiliations with Malaysian authors. The most commonly employed author keywords by previous researchers were “bibliometric analysis”, “research evaluation”, “scientometrics”, “citation analysis”, and “co-authorship analysis”. Future research endeavours could concentrate on delving deeper into these subjects and scrutinising novel topics and domains of interest in bibliometric analysis.

Adjectives and adverbs as stylometric analysis parameters

The present study considers the role of adjectives and adverbs in stylometric analysis and authorship attribution. Adjectives and adverbs allow both for variations in placement and order (adverbs) and variations in type (adjectives). This preliminary study examines a collection of 25 English-language blogs taken from the Schler Blog corpus, and the Project Gutenberg corpus with specific emphasis on 3 works. Within the blog corpora, the first and last 100 lines were extracted for the purpose of analysis. Project Gutenberg corpora were used in full. All texts were processed and part-of-speech tagged using the Python NLTK package. All adverbs were classified as sentence-initial, preverbal, interverbal, postverbal, sentence-final, or none-of-the-above. The adjectives were classified into types according to the universal English type hierarchy (Cambridge Dictionary Online, 2021; Annear, 1964) manually by one of the authors. Ambiguous adjectives were classified according to their context. For the adverbs, the initial samples were paired and used as training data to attribute the final samples. This resulted in 600 trials under each of five experimental conditions. We were able to attribute authorship with an average accuracy of 9.7% greater than chance across all five conditions. Confirmatory experiments are ongoing with a larger sample of English-language blogs. This strongly suggests that adverbial placement is a useful and novel idiolectal variable for authorship attribution (Juola et al., 2021). For the adjective, differences were found in the type of adjective used by each author. Percent use of each type varied based upon individual preference and subject-matter (e.g. Moby Dick had a large number of adjectives related to size and color). While adverbial order and placement are highly variable, adjectives are subject to rigid restrictions that are not violated across texts and authors. Stylometric differences in adjective use generally involve the type and category of adjectives preferred by the author. Future investigation will focus, likewise, on whether adverbial variation is similarly analyzable by type and category of adverb.

A comparison of latent semantic analysis and correspondence analysis of document-term matrices

Abstract Latent semantic analysis (LSA) and correspondence analysis (CA) are two techniques that use a singular value decomposition for dimensionality reduction. LSA has been extensively used to obtain low-dimensional representations that capture relationships among documents and terms. In this article, we present a theoretical analysis and comparison of the two techniques in the context of document-term matrices. We show that CA has some attractive properties as compared to LSA, for instance that effects of margins, that is, sums of row elements and column elements, arising from differing document lengths and term frequencies are effectively eliminated so that the CA solution is optimally suited to focus on relationships among documents and terms. A unifying framework is proposed that includes both CA and LSA as special cases. We empirically compare CA to various LSA-based methods on text categorization in English and authorship attribution on historical Dutch texts and find that CA performs significantly better. We also apply CA to a long-standing question regarding the authorship of the Dutch national anthem Wilhelmus and provide further support that it can be attributed to the author Datheen, among several contenders.

A Multi-Dictionary Approach to Abstractness/Concreteness-Based Authorship Attribution


 
 
 We present some early results from a research project aimed at exploring the usefulness of abstractness/concreteness as stylistic features for authorship attribution. We conjecture that authors use abstract/concrete words and phrases in suf- ficiently unique ways, so that machine learning classifiers can learn to distinguish the individual authors’ writing styles. Our approach is based on using the abstractness rat- ings of words and phrases from texts with established au- thorship to generate training vectors for different machine learning classifiers. The combined word/phrase ratings are extracted from two separate abstractness dictionaries – an approach that yields stronger results than using single ab- stractness dictionaries. The paper describes the details of our methodology and compares the results to those obtained using traditional authorship attribution stylistic features. The limitations of our current methodology and directions for further research are outlined at the end of the paper.
 
 

“I would I had that corporal soundness”: Pervez Rizvi's Analysis of the Word Adjacency Network Method of Authorship Attribution

Abstract In his two-part article ‘An Analysis of the Word Adjacency Network Method—Part 1—The evidence of its unsoundness’ and ‘Part 2—A true understanding of the method’ Digital Scholarship in the Humanities, 38: 347-78 (2022), Pervez Rizvi attempts to replicate the Word Adjacency Network (WAN) method for authorship attribution and show that it does not produce the new knowledge that we, its inventors, claim for it. In the present essay, we will show that Rizvi misrepresents fundamental aspects of the WAN method, that his attempted replication fails not because the method is flawed but because he erred in replicating it, and that Rizvi misunderstands key aspects of the mathematics of Information Theory that the method uses.

Hacking stylometry with multiple voices: Imaginary writers can override authorial signal in Delta

Abstract It is a basic assumption of stylometry that texts written by the same person show greater stylometric similarity even if published under multiple pennames. Statistical authorship attribution strongly relies on the ability of Burrows’s Delta and its variants to cluster one author together regardless of pseudonyms. At the same time, the very first computational discoveries by the founder of modern stylometry showed that a single author is capable of producing multiple voices (Burrows, 1987, Computation into Criticism: A Study of Jane Austen’s Novels and an Experiment in Method. Clarendon Press). We investigate two authors whose stylistically autonomous pennames seem to deceive Delta and override authorial signals: a Portuguese poet Fernando Pessoa and a French novelist Romain Gary. Pessoa managed to create at least three pennames (the author himself used the term ‘heteronym’) who exhibit all traits of individual human beings from the stylometric point of view. Gary’s alter ego Emile Ajar, who was an intentional literary mystification, also demonstrates traits of stylometric autonomy. At the same time, other pseudonyms used by Gary lack that autonomy completely. Our investigation shows that there appears to be a continuum between a purely formal use of a penname, which brings almost no distinction from the real name of an author, and a strong literary sub-personality such as those created by Pessoa.

Exploring the domain of relationship between happiness management in organizations and the environment

PurposeOrganizational happiness has received exponential attention in recent years. To offer an over-view for future research gap, this article produces a comprehensive review by combining bibliometric analysis and interviews to key authors in the field. The main objective of this paper is to show the state of research regarding the environment in the management of happiness in organizations: the evolution of scientific activity, current trends in authorship, topics and future setting research agenda.Design/methodology/approachThe methodological process focuses on a mixed method. A systematic review of the relevant literature; bibliometric analysis and network mapping in the Web of Science and Scopus data-bases; bibliometric network analysis of authorship, citation and co-occurrence of key words in scientific publications.FindingsThe results reveal that happiness management is gaining importance and, moreover, more than half of the publications about happiness management are related to the environment in which the organizations are immersed. Therefore, the study provides some research directions and insists on role of environment to better understand the theoretical and practical perspectives. Likewise, bibliometric analysis and interviews allow to measure quality, impact, productivity and scientific evolution which are increasingly valued in order to identify the main concepts and topics that are considered key, drivers of research and those gaps that should be addressed in future research work for the conceptual framework of happiness management in organizations.Originality/valueConclusions are drawn that promoting corporate social responsibility strategies, aimed at fostering sustainability and care for the environment result in the well-being of organizations and the performance of their workers are highlighted.

Frequent-words analysis for forensic speaker comparison

While many authorship analysis techniques could be applied to any type of linguistic data, there is very limited research on their application on transcriptions of spontaneous speech to help identify the speaker. In authorship analyses, frequency analysis of function words has been quite a successful feature since, when writing a text, people tend to use different function words in different frequencies. Thus, this feature is sensitive to author style while it remains relatively insensitive to the topic of the text. In this paper, we make the cross-over to speech samples and test whether frequency analysis of the most common words in speech, which are mostly function words, has potential as a speaker discriminant. We propose a method within the likelihood ratio framework for court applicability. Our approach takes into account both the similarity and typicality of word frequencies by employing a method using percentile-rank for feature extraction. We apply our method on the forensically relevant dataset FRIDA, achieving good results even when a limited amount of data is available.

Attributions of Authorship in the Gentleman’s Magazine, 1827–1830: A Supplement to the Union List

The following list consists of eighty-six new attributions of authorship (and three corrected ones) of anonymous, pseudonymous, or incompletely signed letters, articles, drawings, reviews, poems, obituaries, and staff notes appearing in the Gentleman’s Magazine (hereafter GM) during the years 1827–1830. The period covered in this list encompasses the first four years of the editorial stewardship of John Bowyer Nichols, John Nichols’s son and longtime partner, who succeeded his father as sole conductor of the magazine upon the latter’s death on 26 November 1826 and thus assumed the persona of ‘Sylvanus Urban’, the GM’s fictitious editor, in his own right. The authorial attributions that follow constitute the latest installment in my ongoing efforts to supplement my Attributions of Authorship in the Gentleman’s Magazine, 1731–1868: An Electronic Union List (Charlottesville, VA: Bibliographical Society of the University of Virginia, 2003), https://bsuva.org/bsuva/gm2 (accessed 28 February 2023). The overwhelming majority of the fifty-one contributors whose writings and drawings appear below consists of antiquaries, clergymen, artists, and architects, a predictable assemblage consistent with the fact that for some years John Bowyer Nichols had been reorienting the GM more and more along the path of antiquarian concerns. Other contributors represented in the following list include poets, historians, schoolmasters, members of the legal community, art collectors, and a Keeper of Manuscripts at the British Museum, as well as various miscellaneous writers.

A Bibliometric Analysis of the Research on Social Attitudes Towards LGBT Community (2002–2022)

ABSTRACT A bibliometric analysis was conducted to map out trends in publications on attitudes toward the LGBT community based on the 470 documents retrieved from the SCOPUS database for 2002–2022. The results revealed that the United States is the leading country contributing to the publications on attitudes toward the LGBT community and has a strong impact in the field (64.68%). The authorship analysis revealed that Flores, Woodford, and Worthen from the United States are the leading researchers in this field. Analysis of publication sources showed that the Journal of Homosexuality is the top publisher of findings on the LGBT community whereas the Journal of Interpersonal Violence and Sexuality and Culture have gained more traction among researchers in recent years. The analysis of the co-occurrence of author’s keywords indicated that transgender is the gender group that is the most researched compared to other sexual identities. Negative attitudes such as homophobia, discrimination and being heterosexist toward one’s sexuality or same-sex marriage are the current research foci. Religion and culture are seen as important predictors of attitudes about homosexuality and same-sex marriage policy. The study addresses the gaps in the literature by recommending future researchers to investigate attitudes toward other gender identities as a result of the revolution in sexual identities.