Properties Of Text Research Articles

Authorship Attribution of Social Media and Literary Russian-Language Texts Using Machine Learning Methods and Feature Selection

Authorship attribution is one of the important fields of natural language processing (NLP). Its popularity is due to the relevance of implementing solutions for information security, as well as copyright protection, various linguistic studies, in particular, researches of social networks. The article is a continuation of the series of studies aimed at the identification of the Russian-language text’s author and reducing the required text volume. The focus of the study was aimed at the attribution of textual data created as a product of human online activity. The effectiveness of the models was evaluated on the two Russian-language datasets: literary texts and short comments from users of social networks. Classical machine learning (ML) algorithms, popular neural networks (NN) architectures, and their hybrids, including convolutional neural network (CNN), networks with long short-term memory (LSTM), Bidirectional Encoder Representations from Transformers (BERT), and fastText, that have not been used in previous studies, were applied to solve the problem. A particular experiment was devoted to the selection of informative features using genetic algorithms (GA) and evaluation of the classifier trained on the optimal feature space. Using fastText or a combination of support vector machine (SVM) with GA reduced the time costs by half in comparison with deep NNs with comparable accuracy. The average accuracy for literary texts was 80.4% using SVM combined with GA, 82.3% using deep NNs, and 82.1% using fastText. For social media comments, results were 66.3%, 73.2%, and 68.1%, respectively.

Information extraction from scanned invoice images using text analysis and layout features

While storing invoice content as metadata to avoid paper document processing may be the future trend, almost all of daily issued invoices are still printed on paper or generated in digital formats such as PDFs. In this paper, we introduce the OCRMiner system for information extraction from scanned document images which is based on text analysis techniques in combination with layout features to extract indexing metadata of (semi-)structured documents. The system is designed to process the document in a similar way a human reader uses, i.e. to employ different layout and text attributes in a coordinated decision. The system consists of a set of interconnected modules that start with (possibly erroneous) character-based output from a standard OCR system and allow to apply different techniques and to expand the extracted knowledge at each step. Using an open source OCR, the system is able to recover the invoice data in 90% for English and in 88% for the Czech set.

Establishing an Operational Model of Rating Scale Construction for English Writing Assessment

Rating scales for writing assessment are critical in that they determine directly the quality and fairness of such performance tests. However, in many EFL contexts, rating scales are made, to certain extent, based on the intuition of teachers who strongly need a feasible and scientific route to guide their construction of rating scales. This study aims to design an operational model of rating scale construction with English summary writing as an example. Altogether 325 university English teachers, 4 experts in language assessment and 60 English majors in China participated in the study. 20 textual attributes were extracted, through text analysis, from China’s Standards of English Language Ability (CSE), theoretical construct of summary writing, comments on sample summary writing essays from 8 English teachers and their personal judgement. The textual attributes were then investigated through a large-scale questionnaire survey. Exploratory factor analysis and expert judgement were employed to determine rating scale dimensions. Regression analysis and expert judgement were conducted to determine the weighting distribution across all dimensions. Based on such endeavors, a tentative operational model of rating scale construction was established, which can also be applied and adapted to develop rating scales in other writing assessment. 

Studying the Fifty Seven and the Fifty Eight Verse from Surah Alaraf in the Light of Text Attribution

Attribution is considered as one of the means which helps to improve speech for it avoids the text from being scattered by gathering its parts and giving it cohesion and coherence. The research is built on studying the fifty seven and the fifty eight verse from surah Alaraf in the light of text Attribution and this required three demands the first one is showing the opinions of the explainers and the second is studying the means of text casting while the third demand was represented in the significance of the word (all). The most important results this study reached is that there was no use of pronoun with transference from third person singular into direct speech but instead of that this example shows returning to the speech of one of the addressee who is the prophet of god Mousses and also showed the effect of attribution in revealing interpreters opinions which was not shown before.

From the Editorial Archive of the Journals "Vremya" and "Epokha" Published by the Dostoevsky Brothers

The journals "Vremya" and "Epokha" attracted the attention of researchers primarily in connection with the personality and work of the writer Fyodor Dostoevsky, who took an active part in the journals published by his brother, Mikhail Dostoevsky. This fact determined the nature of the study of these journals: they are least researched as independent periodicals in the 1860s, with most of the works being devoted to specific aspects. Despite the increased attention of researchers to "Vremya" and "Epokha" in recent decades, many questions remain unresolved: the editorial and royalty policy of journals and the financial side of the publication have not been sufficiently studied, the key problem of attribution of anonymous and pseudonymous journal articles has not been fully resolved, i.e., in regard to the co-authorship and editorial work of F. M. Dostoevsky, and the determination of the degree of the writer’s contribution to the articles by other authors. The article not only enumerates the problems of studying "Vremya" and "Epokha" and the role of Dostoevsky in these journals; it also presents an analysis of certain materials from the editorial archive. The entries of a credit and debit notebook offer insight into the financial side of the publication (costs and income of the editorial office), the conduct of editorial and publishing affairs by the Dostoevsky brothers, and allow to judge the success of their enterprise. A payroll record includes receipts from employees for the honoraria received for their work and publications. The editing fee system is determined by the ratio of the costs of fees to the amounts received by the journal staff on the payroll record. The materials from the editorial archives of "Vremya" and "Epokha" analyzed in this article contain valuable information for attribution of anonymous and pseudonymous journal texts. The analysis of editorial records, correspondence of journal employees, memoirs and other documentary sources allow to confirm existing attributions or find contradictions in them and highlight the most reliable ones. The analysis of the materials from the editorial archives of "Vremya" and "Epokha" significantly expand the understanding of these two periodicals of the 2nd half of the 1860s and the writer’s related activities as part of his creative work. These documents open up broad prospects for further study and search for answers to questions.

Through the eyes of the founder: CEO characteristics and firms’ regulatory filings

AbstractWe examine whether textual attributes of founder‐led firms’ regulatory filings reflect founder‐CEO characteristics and whether investors consider this relation when assessing firm value. We build on prior research that shows founders have unique personality attributes, particularly overoptimism. Our results suggest that 10‐K text for founder‐led firms is characterized by “excess” optimism relative to current and future realized earnings and relative to non‐founder‐led firms. The effect is mitigated for firms with large auditors, high litigation risk and high analyst following. Based on the stock price at the 10‐K release, investors do not appear to appropriately discount the tone, resulting in predictable negative returns during the year subsequent to the 10‐K release, particularly for the first 2 years after firms go public. Collectively, our findings contribute to the existing literature examining the effects of executives on firm disclosure by providing initial evidence about the conditions under which firms’ scripted narrative disclosures reflect CEO characteristics.

Hapax remains: Regularity of low-frequency words in authorial texts

Abstract This article highlights the usual overlook in the literature of regular occurrences of low-frequency words (hapax legomena) in specific authors’ texts. This overlook arises from a linguistic assumption of non-systematic and context-dependent low-frequency word occurrences in extensive texts, and from the tendency of SVM methods to mark low-frequency words as irrelevant compared to the more frequent lexicon (e.g. Boukhaled, M. A. and Ganascia, J.-G. (2015). Using function words for authorship attribution: bag-of-words vs. sequential rules. In The 11th International Workshop on Natural Language Processing and Cognitive Science, October 2014, Venice, Italy. de Gruyter, Natural Language Processing and Cognitive Science Proceedings 2014, pp. 115–122.). Many approaches to authorship attribution are based on the n most frequent ‘function words’, which (1) are grammatically essential, frequent, and therefore included in each text; (2) are not affected by the topic of the text; and (3) reflect the unintentional linguistic activity of the author (Binongo, J. N. G. (2003). Who wrote the 15th book of Oz? An application of multivariate analysis to authorship attribution. Chance, 16(2): 9–17). Hapax legomena meet these conditions as well, except frequency (Baayen, H., van Halteren, H., and Tweedie, F. (1996). Outside the cave of shadows: using syntactic annotation to enhance authorship attribution. Literary and Linguistic Computing, 11(3): 121–32). We test the hypothesis that hapax legomena may work for purposes of authorship attribution based on selecting only hapaxes from whole texts (or randomly selected tokens of hapaxes) while using a specific pre-processed input (eigendecomposition of a cosine distance matrix) to the SVM classifier. This method evaluated the attribution of texts from fourteen Czech authors (yielding ninety-one pairs in total) and Evert, S., Proisl, T., Jannidis, F. et al. (2017). Understanding and explaining Delta measures for authorship attribution. Digital Scholarship in the Humanities, 32(2): 4–16 data set, and proved itself a suitable tool for identifying authors of previously unknown texts. Our method identifies a sparse network of regular occurrences of low-frequency words in different authors’ texts.

TACN: A Topical Adversarial Capsule Network for textual network embedding

Combining topological information and attributed information of nodes in networks effectively is a valuable task in network embedding. Nevertheless, many prior network embedding methods regarded attributed information of nodes as simple attribute sets or ignored them totally. In some scenarios, the hidden information contained in vertex attributes are essential to network embedding. For instance, networks that contain vertexes with text information play an increasingly important role in our life, including citation networks, social networks, and entry networks. In these textual networks, the latent topic relevance information of different vertexes contained in textual attributes information are valuable in the network analysis process. Shared latent topics of nodes in networks may influence the interaction between them, which is critical to network embedding. However, much prior work for textual network embedding only regarded the text information as simple word sets while ignored the embedded topic information. In this paper, we develop a model named Topical Adversarial Capsule Network (TACN) for textual network embedding, which extracts a low-dimensional latent space of the original network from node structures, vertex attributes, and topic information contained in text of nodes. The proposed TACN contains three parts. The first part is an embedding model, which extracts the embedding representation from the topological structure, vertex attributes, and document-topic distributions. To ensure a consistent training process by back-propagation, we generate document-topic distributions by the neural topic model with Gaussian Softmax constructions. The second part is a prediction model, which is used to exploit labels of vertices. In the third part, an adversarial capsule model is used to help distinguish the latent representations from node structure domain, vertex attribute domain, or document-topic distribution domain. The latent representations, which may come from the three domains, are the output of the embedding model. We incorporate the adversarial idea into the adversarial capsule model to combine the information from these three domains, rather than to distinguish the representations conventionally. Experiments on seven real-world datasets validate the effectiveness of our method.

Using Data Compression to Build a Method for Statistically Verified Attribution of Literary Texts.

We consider the problems of the authorship of literary texts in the framework of the quantitative study of literature. This article proposes a methodology for authorship attribution of literary texts based on the use of data compressors. Unlike other methods, the suggested one gives a possibility to make statistically verified results. This method is used to solve two problems of attribution in Russian literature.

Enhanced urban functional land use map with free and open-source data

ABSTRACT The study aims at developing an applicable methodology to produce the functional land-use map using only free and open-source data. Top-view Sentinel image and ground-view Open Street Map (OSM) data are chosen due to their extensive availability. The three-stage framework, including object-based image analysis, OSM data cleaning, and ontology-based decision fusion, is proposed and implemented with open-source tools. We applied the developed approach to districts 1, 4, and 7 of HoChiMinh city, representing the complexities of the dynamic change in big cities. The result showed a good functional land use map with 78.70% overall accuracy. The outcome presents the mismatch between the data-driven approach and human knowledge, which can be improved by ontology-based fusion with OSM data. The ontology-based framework comprises the common urban land-use classes and OSM attributes, which can be applied and extended in other urban areas. Additional text attributes may be applicable only locally and can be modified in our open-source framework. Object-based image analysis takes advantage of Google Earth Engine computing power, whereas ontology-based processing works well on a local computer. In future studies, adopted natural language processing to pre-process OSM data and ontology-based fusion will be implemented on the cloud-computing platform to enhance computational efficiency.

Assessing the combination of DistilBERT news representations and difusion topological features to classify fake news

Fake news (FN) have affected people’s lives in unimaginable ways. The automatic classification of FN is a vital tool to prevent their dissemination and support fact-checking. Related work has shown that FN spread faster, deeper, and more broadly than truthful news on social media. Deep learning has produced state-of-the-art solutions in this field, mainly based on textual attributes. In this paper, we propose to combine compact representations of the textual news properties generated using DistilBERT, with topological metrics extracted from their propagation network in social media. Using a dataset related to politics and distinct learning algorithms, we extensively assessed the components of the proposed solution. Regarding the textual attributes, we reached results comparable to stateof-the-art solutions using only the news title and contents, which is useful for FN early detection. We assessed the influential topological metrics, and the effect of their combination with the news textual features. We also explored the use of ensembles. Our results were very promising, revealing the potential of the features proposed and the adoption of ensembles.

Auditors’ Assessment and Response to Audit Risks: Evidence from Content Analyses of Critical Audit Matters

This study examines whether critical audit matter (CAM) disclosures required by Auditing Standard 3101 have communication value through content analyses. First, we employ salience scores to capture the importance of audit risk and scope in describing CAMs as assessed by the auditor. Due to limited information processing ability, human readers assign more importance to prominent parts and find them more informative, which is captured by salience score. Second, we count words related to the resolution activities to analyze how actively the auditors resolve the CAM. The results show that these textual attributes of CAMs are related to the proxies for client business risk, audit risk, auditor business risk, auditor attributes, and audit committee effectiveness. We also document that audit fees are higher with higher salience scores in the audit scope. These results indicate that auditors make efforts into actual communication via CAM disclosures.

Text-Aware Predictive Monitoring of Business Processes

The real-time prediction of business processes using historical event data is an important capability of modern business process monitoring systems. Existing process prediction methods are able to also exploit the data perspective of recorded events, in addition to the control-flow perspective. However, while well-structured numerical or categorical attributes are considered in many prediction techniques, almost no technique is able to utilize text documents written in natural language, which can hold information critical to the prediction task. In this paper, we illustrate the design, implementation, and evaluation of a novel text-aware process prediction model based on Long Short-Term Memory (LSTM) neural networks and natural language models. The proposed model can take categorical, numerical and textual attributes in event data into account to predict the activity and timestamp of the next event, the outcome, and the cycle time of a running process instance. Experiments show that the text-aware model is able to outperform state-of-the-art process prediction methods on simulated and real-world event logs containing textual data.

Cloud deployment of game theoretic categorical clustering using apache spark: An application to car recommendation

Personal vehicles are invariably being preferred over public transport nowadays. Contact-less feature inspection and analysis based on personal preferences will be in high demand among customers in the post-pandemic world. A comprehensive online car recommendation system will be the customers’ spontaneous choice to understand and select the features of vehicles. However, the clustering of such categorical features is a challenging task as it is difficult to compare two textual attributes. In this paper, we have designed a cloud-based system that will automatically address this issue. Motivated by the cooperative game theory and fuzzy technique, and integrating the concept of Shapley theorem, a categorical data clustering algorithm has been developed. At the same time, to overcome the major limitation of having a high time complexity of the order O(n2) associated with the Shapley computation, the proposed algorithm has been distributed using Apache Spark’s Map Reduce architecture in Google Cloud Platform. The model has been thoroughly validated based on its performance on several synthetic as well as real data sets. Finally, a car recommendation system has been proposed and tested on three car sell data sets. The proposed approach outperforms the corresponding existing categorical clustering approaches in terms of various clustering validity indices. To the best of the authors’ knowledge, this is the first attempt to apply Map Reduce based Shapley computation over the categorical clustering, which can find its application beyond the proposed car recommendation system as well.

CONCEPTUALIZING A FRAMEWORK FOR ANALYSING COLLEGE STATISTICS TEXTBOOKS IN TERMS OF TEXT ACCESSIBILITY

This article develops an analytical framework for analysing college (tertiary) statistics textbooks in terms of text accessibility by integrating the text, the reader, and the content into the framework. Five accessibility attributes of science texts were adapted to conceptualize the accessibility of statistics texts. For each accessibility attribute, two components were proposed by referring to the literature on the readability of mathematics texts as well as the characteristics of statistics. The feasibility of the framework is demonstrated by analysing sample statistics texts. The contributions and potential of the framework are discussed.

MultiTalk: A Highly-Branching Dialog Testbed for Diverse Conversations

We study conversational dialog in which there are many possible responses to a given history. We present the MultiTalk Dataset, a corpus of over 320,000 sentences of written conversational dialog that balances a high branching factor (10) with several conversation turns (6) through selective branch continuation. We make multiple contributions to study dialog generation in the highly branching setting. In order to evaluate a diverse set of generations, we propose a simple scoring algorithm, based on bipartite graph matching, to optimally incorporate a set of diverse references. We study multiple language generation tasks at different levels of predictive conversation depth, using textual attributes induced automatically from pretrained classifiers. Our culminating task is a challenging theory of mind problem, a controllable generation task which requires reasoning about the expected reaction of the listener.

Fusion of text and graph information for machine learning problems on networks.

Today, increased attention is drawn towards network representation learning, a technique that maps nodes of a network into vectors of a low-dimensional embedding space. A network embedding constructed this way aims to preserve nodes similarity and other specific network properties. Embedding vectors can later be used for downstream machine learning problems, such as node classification, link prediction and network visualization. Naturally, some networks have text information associated with them. For instance, in a citation network, each node is a scientific paper associated with its abstract or title; in a social network, all users may be viewed as nodes of a network and posts of each user as textual attributes. In this work, we explore how combining existing methods of text and network embeddings can increase accuracy for downstream tasks and propose modifications to popular architectures to better capture textual information in network embedding and fusion frameworks.

Anonymous Equity Research

ABSTRACTCrowdsourced financial information platforms often allow content contributors to publish equity research anonymously. This study examines whether investors value or discount information in anonymous equity research. In the short window around research releases, we find that investors’ stock price reaction to anonymous research is muted in comparison to nonanonymous research. Consistent with credibility concerns influencing investor response, we document that this discount to anonymous research dissipates as the monitoring of content contributors intensifies and as authors develop a reputation for high‐quality reporting. In addition, we perform a content analysis on the research reports and find that the muted market reaction to anonymous equity research is robust to controlling for textual attributes of information content, further supporting our inference that investors’ are concerned about the credibility of anonymous equity research.

The study of memoir texts in modern ‘linguistics: a brief analytical overview

The goal of this article is to present a brief analytical overview of the modern linguistic studies of memoir texts. The object of this research is the scientific works of the linguists of two recent decades dedicated to memoirs. The subject is the polemical questions in the linguistic descriptions of memoir texts. The article examines the problem of identification of genre status of memoirs and systematization of genre forming attributes of the memoir texts. Various approaches towards their classification are described. Special attention is given to the aspects of studying memoirs in modern linguistics. The key research method is the traditional for linguistics analytical-descriptive method for reviewing the scientific literature on the topic. The author proves heightened attention of the Russian linguistics towards studying memoir texts. It is revealed that the Russian scholars attribute memoirs to the documental, documental-fictional, or documental-publicistic genres, as well as propose various approaches towards their classification, which is substantiated by different interpretation of the concept of “memoirs”. It is also determined that multiple research of memoir texts are cross-disciplinary; however major attention is paid to linguopragmatic and linguopersonological aspects. Emphasis is placed on the memoirs of prominent writers, politicians, and military officers. The author acknowledges that the study of memoir texts in the linguoimagological aspect is promising. The scientific novelty consists in the fact that the acquired results give a systematic perspective on the problem of linguistic research of memoir literature as the Russian national heritage.

Stacked authorship attribution of digital texts

In computational authorship attribution (AA) – the task of identifying the author of a given text based on a set of possible candidates – existing differences across domains, languages or input settings may require using knowledge from multiple sources, ranging from surface character patterns to deeper semantics and others. Moreover, since increasing the model complexity may easily lead to overfitting, sources of this kind have to be selected judiciously according to each particular input. Based on these observations, this article introduces a novel approach to AA consisting of stacked classifiers built from multiple knowledge sources - words, characters, part-of-speech n-grams, syntactic dependencies, word embeddings and more - that are dynamically included in the AA model according to the relevant input. In doing so, we would like to show that a stacking approach not only outperforms previous work in the field, but also that dynamic model selection outperforms the use of any of the individual components alone. The current model - called DynAA - is evaluated in a number of AA scenarios covering multiple languages, domains and input sizes, and is shown to generally outperform a number of baseline alternatives, including convolutional neural networks, BERT and others.