Text-based Methods Research Articles

Blended online and face-to-face art therapy

This article focuses on a blended art-based practice that uses a combination of face-to-face, online, mobile and e-mail text-based methods. Blended art therapy alternates between digital and face-to-face formats complementing each other allowing clients to become autonomous and adapt to changing life circumstances. The approach encourages clients to take an active role in the distant treatment while undertaking continuous home art engagement tasks in between sessions. Switching between different digital, virtual and terrestrial formats will be described in this article. The outcomes discussed indicate certain client groups may benefit from a blended method approach. Attention will be given to the experiences of sensory perception, intimacy and relational proximity, during the virtual phases of the work. This article will also highlight observations in relation to the ways in which attachment dynamics have been identified and worked with in the face-to-face phase of therapy.

HiFiSketch: High Fidelity Face Photo-Sketch Synthesis and Manipulation.

With the rapid development of generative adversarial networks, face photo-sketch synthesis has achieved promising performance and playing an increasingly important role in law enforcement as well as entertainment. However, most of the existing methods only work under the condition of no interference, and lack of generalization ability in wild scenes. The fidelity of the images generated by the existing methods are insufficient, and the manipulation ability according to text description is unavailable. Directly applying existing text-based image manipulation methods on face photo-sketch scenario may lead to severe distortions due to the cross-domain challenges. Therefore, we propose a novel cross-domain face photo-sketch synthesis framework named HiFiSketch, a network that learns to adjust the weights of generators for high-fidelity synthesis and manipulation. It can realize the translation of images between the photo domain and the sketch domain, and modify results according to the text input in the meanwhile. We further propose a cross-domain loss function, which can effectively preserve facial details during face photo-sketch synthesis. Extensive experiments on four public face sketch datasets show the superiority of our method compared to existing methods. We further present text-based face photo-sketch manipulation and sequential face photo-sketch manipulation for the first time to demonstrate the effectiveness of our method on high fidelity face photo-sketch synthesis and manipulation.

An Image-Based Approach to Measuring Human Values

This study aims to explore the potential of using a novel image-based approach to measuring individuals’ human values. This could result in higher-quality measurements by circumventing the drawbacks of the text-based methods prone to social biases affecting the truthful interpretation of complex verbal constructions and a low respondent engagement due to lengthy interviews. A review of the academic literature on image-based research into human values is performed and validated by our own empirical research on a representative sample of the Latvian population to compare the results of our image-based approach with the text-based approach. Our findings suggest that currently, most image-based methodologies for measuring the values and motivations of individuals lack structure and verified application. There is no precise and widely accepted methodology. However, a well-developed image-based research methodology has the potential to fill in this gap. The results confirm that an individual’s values can be identified and structured into a personal hierarchy by applying both text-based methods (asking respondents to evaluate written statements) and image-based methods (evaluation of selected images representing specific values). Our study employs a new image-based approach that seems to offer a more straightforward and more precise way of measuring values compared to the text-based approach.

Education is a Woman’s Asset in Elizabeth Gaskell’s Cousin Phillis

The Victorian period was characterised by its landmark on the swift change of moral and social codes leaving an impact on the status of women which prompted reflections by thinkers and authors. The novelist, Elizabeth Gaskell (1810-1865), breaks new grounds by drawing attention to strategic education which helps women to construct gender identity. As such, education that enhances practical achievements for women stands for an empowering asset that serves to revisit the prevalent conventional norms of training women merely for the accomplishment of domestic tasks. This argument is backed up by supporting details provided through the applied text-based analysis method. Unlike readings of Cousin Phillis (1864) showing a woman’s educational outcome as limited to a failed romantic experience, a deep reading of Gaskell’s text provides a substantial understanding of the impact of a woman’s education which enlightens a woman’s mind to develop from ignorance to knowledge, and from ‘foolishness’ to wisdom in the symbolic setting of Hope Farm. Therefore, the experience of the unaccomplished love affair is rewritten in terms of making it a womanly cultural experience that broadens her knowledge of herself and her practical needs in a pastoral environment. Becoming acquainted with the Latin and Italian languages and literature helps the character’s mind to transcend the limited romantic dimension in the promotion of the female identity construction process that is organically connected with the national identity.

Accessing the Climate Change Impacts in China through a Literature Mapping.

In the 21st century, carbon dioxide emissions have led to adverse climate changes; meanwhile, the impact of climate change has imposed challenges worldwide, particularly in developing countries, and China is one of the most affected countries. Assessing the impact of climate change requires handling a large amount of data in the literature comprehensively. In this study, a text-based classification method and literature mapping were used to process the massive literature and map it according to its location. A total of 39,339 Chinese academic studies and 36,584 Chinese master’s and doctoral theses, from 2000 to 2022, with evidence of the impact of climate change were extracted from the China National Knowledge Infrastructure database. Our results show that the literature on climate change impacts has exploded during the last decades. This indicates that increasing attention to the intensified impact of climate change in China has been paid. More importantly, by mapping the geolocation of the literature into spatial grid data, our results show that over 36.09% of the land area shows clear evidence of climate change. Those areas contribute to 89.29% of the gross domestic product (GDP) and comprise 85.06% of the population in China. Furthermore, the studies we collected on the climate change impacts showed a huge spatial heterogeneity. The hotspot areas of research were generally located in developed regions, such as the BTH urban agglomeration and Yangtze River Economic Zone, major agricultural production areas such as Shandong and Henan, and ecologically fragile regions including Yunnan, Xinjiang, and Inner Mongolia. Considering the imbalance spatially of the evidence of climate change can help in a better understanding of the challenges in China imposed by climate change. Appraising the evidence of climate change is of great significance for adapting to climate change, which is closely related to the natural ecosystem services and human health. This study will provide policy implications for coping with climatic events and guide future research.

Playfulness as a virtuous disposition: its affinity with dramatic play and aretaic practice

ABSTRACT This study investigates the nature of playfulness as a personal virtuous disposition influential to the practice and growth of virtues. It is conducted within the playful space of dramatic play, in the context of the drama course of a teacher preparation programme. It combines two qualitative approaches, a single case study and a narrative inquiry. A small group of student primary teachers participated in the data collection process that rested both on direct and indirect narrative text-based methods: reflective diaries, the teacher’s journal, a semi-structured interview and photographs of the course’s workshops. The findings overall demonstrate that a nexus of internal and external conditions of the participants’ embodiment of dramatic play in synergy with their flow experiences encouraged the constitution of their playfulness as a virtuous disposition. In this aretaic space of their playfulness, they grew three virtues: parrhesia, friendship and self-knowledge.

"Broadcast your gender." A comparison of four text-based classification methods of German YouTube channels.

Social media platforms provide a large array of behavioral data relevant to social scientific research. However, key information such as sociodemographic characteristics of agents are often missing. This paper aims to compare four methods of classifying social attributes from text. Specifically, we are interested in estimating the gender of German social media creators. By using the example of a random sample of 200 YouTube channels, we compare several classification methods, namely (1) a survey among university staff, (2) a name dictionary method with the World Gender Name Dictionary as a reference list, (3) an algorithmic approach using the website gender-api.com, and (4) a Multinomial Naïve Bayes (MNB) machine learning technique. These different methods identify gender attributes based on YouTube channel names and descriptions in German but are adaptable to other languages. Our contribution will evaluate the share of identifiable channels, accuracy and meaningfulness of classification, as well as limits and benefits of each approach. We aim to address methodological challenges connected to classifying gender attributes for YouTube channels as well as related to reinforcing stereotypes and ethical implications.

Using deep learning and electronic health records to detect Noonan syndrome in pediatric patients

PurposeThe variable expressivity and multisystem features of Noonan syndrome (NS) make it difficult for patients to obtain a timely diagnosis. Genetic testing can confirm a diagnosis, but underdiagnosis is prevalent owing to a lack of recognition and referral for testing. Our study investigated the utility of using electronic health records (EHRs) to identify patients at high risk of NS. MethodsUsing diagnosis texts extracted from Cincinnati Children’s Hospital’s EHR database, we constructed deep learning models from 162 NS cases and 16,200 putative controls. Performance was evaluated on 2 independent test sets, one containing patients with NS who were previously diagnosed and the other containing patients with undiagnosed NS. ResultsOur novel method performed significantly better than the previous method, with the convolutional neural network model achieving the highest area under the precision-recall curve in both test sets (diagnosed: 0.43, undiagnosed: 0.16). ConclusionThe results suggested the validity of using text-based deep learning methods to analyze EHR and showed the value of this approach as a potential tool to identify patients with features of rare diseases. Given the paucity of medical geneticists, this has the potential to reduce disease underdiagnosis by prioritizing patients who will benefit most from a genetics referral.

Legal case document similarity: You need both network and text

Estimating the similarity between two legal case documents is an important and challenging problem, having various downstream applications such as prior-case retrieval and citation recommendation. There are two broad approaches for the task — citation network-based and text-based. Prior citation network-based approaches consider citations only to prior-cases (also called precedents) (PCNet). This approach misses important signals inherent in Statutes (written laws of a jurisdiction). In this work, we propose Hier-SPCNet that augments PCNet with a heterogeneous network of Statutes. We incorporate domain knowledge for legal document similarity into Hier-SPCNet, thereby obtaining state-of-the-art results for network-based legal document similarity.Both textual and network similarity provide important signals for legal case similarity; but till now, only trivial attempts have been made to unify the two signals. In this work, we apply several methods for combining textual and network information for estimating legal case similarity. We perform extensive experiments over legal case documents from the Indian judiciary, where the gold standard similarity between document-pairs is judged by law experts from two reputed Law institutes in India. Our experiments establish that our proposed network-based methods significantly improve the correlation with domain experts’ opinion when compared to the existing methods for network-based legal document similarity. Our best-performing combination method (that combines network-based and text-based similarity) improves the correlation with domain experts’ opinion by 11.8% over the best text-based method and 20.6% over the best network-based method. We also establish that our best-performing method can be used to recommend/retrieve citable and similar cases for a source (query) case, which are well appreciated by legal experts.

Technology Differentiation, Product Market Rivalry and M&A Transactions

Prior work has mostly studied the relation between product market competition and M&A deals. In this paper, we study how competition and differentiation in technology space relates to M&A transactions. Relying on a new text-based method to map each firm’s competitive position in technology space and to measure the differentiation of a firm’s technology portfolio relative to all other firms, we find that firms with unique and differentiated technology are typical targets while firms with less differentiated technology are more likely to become acquirers. Moreover, firms with unique technology are particularly targeted by close competitors in the product market and receive a higher acquisition price, particularly in case of M&As with close product market firms. Our findings illustrate that a unique and differentiated technology portfolio is an important resource traded in the market for corporate control and a key driver of M&A deals, particularly between close competitors in the product market.

Detecting fake news by enhanced text representation with multi-EDU-structure awareness

Since fake news poses a serious threat to society and individuals, numerous studies have been brought by considering text, propagation and user profiles. Due to the data collection problem, these methods based on propagation and user profiles are less applicable in the early stages. A good alternative method is to detect news based on text as soon as they are released, and a lot of text-based methods were proposed, which usually utilized words, sentences or paragraphs as basic units. But, word is a too fine-grained unit to express coherent information well, sentence or paragraph is too coarse to show specific information. Which granularity is better and how to utilize it to enhance text representation for fake news detection are two key problems. In this paper, we introduce Elementary Discourse Unit (EDU) whose granularity is between word and sentence, and propose a multi-EDU-structure awareness model to improve text representation for fake news detection, namely EDU4FD. For the multi-EDU-structure awareness, we build the sequence-based EDU representations and the graph-based EDU representations. The former is gotten by modeling the coherence between consecutive EDUs with TextCNN that reflect the semantic coherence. For the latter, we first extract rhetorical relations to build the EDU dependency graph, which can show the global narrative logic and help deliver the main idea truthfully. Then a Relation Graph Attention Network (RGAT) is set to get the graph-based EDU representation. Finally, the two EDU representations are incorporated as the enhanced text representation for fake news detection, using a gated recursive unit combined with a global attention mechanism. Experiments on four cross-source fake news datasets show that our model outperforms the state-of-the-art text-based methods. Our results suggest that considering EDU and its structural features could enhance the text representation for fake news detection.

Hybrid Methods of Bibliographic Coupling and Text Similarity Measurement for Biomedical Paper Recommendation.

The amount of available scientific literature is increasing, and studies have proposed various methods for evaluating document-document similarity in order to cluster or classify documents for science mapping and knowledge discovery. In this paper, we propose hybrid methods for bibliographic coupling (BC) and linear evaluation of text or content similarity: We combined BC with BM25, Cosine, and PMRA to compare their performances with single methods in paper recommendation tasks using TREC Genomics Track 2005datasets. For paper recommendation, BC and text-based methods complement each other, and hybrid methods were better than single methods. The combinations of BC with BM25 and BC with Cosine performed better than BC with PMRA. The performances were best when the weights of BM25, Cosine, and PMRA were 0.025, 0.2, and 0.2, respectively, in hybrid methods. For paper recommendation, the combinations of BC with text-based methods were better than BC or text-based methods used alone. The choice of method should depend on the actual data and research needs. In the future, the underlying reasons for the differences in performance and the specific part or type of information they complement in text clustering or recommendation need to be examined.

Law Smells

Building on the computer science concept of code smells, we initiate the study of law smells, i.e., patterns in legal texts that pose threats to the comprehensibility and maintainability of the law. With five intuitive law smells as running examples—namely, duplicated phrase, long element, large reference tree, ambiguous syntax, and natural language obsession—, we develop a comprehensive law smell taxonomy. This taxonomy classifies law smells by when they can be detected, which aspects of law they relate to, and how they can be discovered. We introduce text-based and graph-based methods to identify instances of law smells, confirming their utility in practice using the United States Code as a test case. Our work demonstrates how ideas from software engineering can be leveraged to assess and improve the quality of legal code, thus drawing attention to an understudied area in the intersection of law and computer science and highlighting the potential of computational legal drafting.

Child-Friendly Authentication (CFA)

A child-friendly authentication system that uses graphic images is an excellent solution to avoid potential electronic risks to children from attackers. This report provides a summary of building a child-friendly authentication system by replacing the traditional text-based authentication method with an image-based authentication method. Where some studies and authors’ research have presented the benefits of using images as passwords and that it is considered the best compared to the text password, on the grounds that the human mind has more ability to remember images faster than text. In addition, this report included some of the applications and examples of using this technology in advance for adults. This report covered many critical points related to building a graphical authentication system for children. The results of previous research have added valuable information to this report. Finally, this report contains the challenges we may encounter while applying this technique, and how to avoid them.

Sarcasm Detection in Online Social Networks Using Machine Learning Methods

Our lives have completely changed since the Internet came into our lives. Role models for people are not only the people around them but people all over the world. Although there are positive aspects of this situation, we will deal with the negative aspects in this study. One of these negative aspects is that people share their ideas on social networks without any supervision. In this way, people who use social networks are told offensive words by people they do not know in real life. Sometimes these words are not directly insulting, but they are expressed sarcastically and annoy the interlocutor. In this study, the detection of sarcastic words in social networks is considered a classification problem. Since the data type used in the proposed method is text-based, both text mining and machine learning methods are used together. In this study, the sarcastic word classification process was carried out using a data set obtained from the Twitter social network, which includes two public classes. The performance of the proposed method was obtained with the Random Forest algorithm with an accuracy of 94.9%.

THE USE OF AUTHENTIC ASSESSMENT IN ENHANCING STUDENTS’ READING COMPREHENSION IN AN ONLINE LEARNING OF ENGLISH LITERATURE

This study aimed at investigating the use of authentic assessment in improving students' reading comprehension in online learning for English Literature courses. This study used a qualitative approach with the type of case study. The research data were online class observations (non-participant observations) and interviews (semi-structured). The participants in this study were selected purposively consisting of lecturers of English education at a university in West Java. The results of class observations showed that lecturer used authentic assessment in online learning for English Literature courses.The lecturer use text-based teaching methods and also some references from journals; and used learning media through WhatsApp groups Zoom Meetings. It showed that the use of authentic assessment can improve students' reading comprehension through evidence of responses to students’ written literary works as a form of presentation task.Keywords: Authentic Assessment, Reading Comprehension, English Literature

SUM: Serialized Updating and Matching for text-based person retrieval

The central problem of text-based person retrieval is how to properly bridge the gap between heterogeneous cross-modal data. Many of the previous works contrive to learn a latent common space to bridge the modality gap and extract modality-invariant feature vectors. Within these methods, the common space mapping and cross-modal information matching operations are conducted in a one-off manner, which aims to extract sufficient discriminative clues from the high-dimensional multi-modal data at first glance, but it is inconsistent with the fact that humans usually follow a step-by-step process to properly recognize and match two objects. Intuitively, the large heterogeneity gap between multi-modal data can be better bridged by gradually analyzing the complex cross-modal relationships. In this paper, we propose a Serialized Updating and Matching (SUM) method for text-based person retrieval to bridge the heterogeneity gap between cross-modal data in a step-by-step manner. The core component of SUM is the proposed Memory Gating Modules (MGM), which can be stacked to gradually update and match features extracted from visual/textual modalities. To fully excavate the correlations lie within multi-granular cross-modal data, two variants are designed to care for both global and fine-grain local information, namely, Global Memory Gating Module (GMGM) and Fine-grained Memory Gating Module (FMGM) with which the updating rate of information at each step is dynamically determined after observing the feature in opposite modality. Moreover, SUM can be flexibly utilized as an add-on to any multi-granular text-based person retrieval methods to further improve the performance. We evaluate our proposed method on two text-based person retrieval datasets CUHK-PEDES and RSTPReid along with two general cross-modal retrieval datasets Flickr8K and Flickr30K to see its generalization ability. Experimental results present that the proposed SUM outperforms existing methods and achieves the state-of-the-art performance.

Impact of model settings on the text-based Rao diversity index

Policymakers and funding agencies tend to support scientific work across disciplines, thereby relying on indicators for interdisciplinarity. Recently, text-based quantitative methods have been proposed for the computation of interdisciplinarity that hold promise to have several advantages over the bibliometric approach. In this paper, we provide a systematic analysis of the computation of the text-based Rao index, based on probabilistic topic models, comparing a classical LDA model versus a neural network topic model. We provide a systematic analysis of model parameters that affect the diversity scores and make the interaction between its different components explicit. We present an empirical study on a real data set, upon which we quantify the diversity of the research within several departments of Fraunhofer and Max Planck Society by means of scientific abstracts published in Scopus between 2008 and 2018. Our experiments show that parameter variations, i.e. the choice of the Number of topics, hyper-parameters, and size and balance of the underlying data used for training the model, have a strong effect on the topic model-based Rao metrics. In particular, we could observe that the quality of the topic models impacts on the downstream task of computing the Rao index. Topic models that yield semantically cohesive topics are less affected by fluctuations when varying over the number of topics, and result in more stable measurements of the Rao index.

Painful Words: The Effect of Battlefield Activity on Conflict Negotiation Behavior

How does battlefield activity affect belligerents’ behavior during wartime negotiations? While scholars have studied when and why warring parties choose to negotiate, few insights explain what negotiators do once seated at the table. I argue that actors engage in obstinate negotiation behavior to signal resolve when undergoing contentious and indeterminate hostilities. I explore this claim by analyzing all negotiation transcripts and associated daily military operations reports from the Korean War. Using text-based, machine learning, and statistical methods, I show that high levels of movement or casualties in isolation produce clear information on future trends, thus yielding more substantive negotiations, while more turbulent activity featuring high movement and casualties in tandem produces cynical negotiations. Moving past contemporary literature, this study explores micro-level dynamics of conflict and diplomacy, builds a theoretical bridge between two perennial views of negotiation, and provides a framework for studying war by applying computational methods to archival documents.

Marked social networks: A new model of social networks based on dynamic behaviors

Social networks are electronically information sharing systems, due to this case, there are many studies on social networks. When studying social networks, text-based solution methods can be used; this type of study is outside the scope of this paper. Some studies have used mathematical models such as graphs, and graphs are mathematical models to represent many things, and social networks are one of them. However, graphs are static models whose structure cannot match the behaviors of social networks. To get rid of this case, Petri nets have been used in some recent studies , however, they have some deficiencies (obtained models are not complete and sound). Because of this case, we modeled social networks by using Petri nets. The resulting model is called Marked Social Network. The marked social network has two types such as Concurrent Marked Social Network and Parallel Marked Social Network. The obtained models were analyzed in case of behavioral and structural properties, and the major properties of the model were determined. All these properties are described in this study.