Textual Features Research Articles

Presentation matters: Surface text features and text quality in written narratives of Dutch high school students with and without dyslexia.

Presentation features such as spelling, punctuation and handwriting can influence the evaluation of general text quality. High school students with dyslexia might therefore be at a disadvantage, as at least their spelling performance is typically poor(er). Furthermore, these students might show less sophisticated linguistic features of texts, such as word length and sentence complexity, that might also be related to text quality. We compared narratives written by Dutch high school students (mean age 13.7 years) with (n = 28) and without (n = 29) dyslexia. Students with dyslexia's texts contained more spelling errors and poorer handwriting quality, but not more punctuation errors. Teacher-rated general text quality was lower for the texts of students with dyslexia in uncorrected versions. When spelling and punctuation errors were corrected, no teacher-rated text quality differences emerged. No differences in linguistic text features were found. Furthermore, spelling, punctuation and, to a lesser extent, number of words per sentence clause were related to ratings of text quality across participants. These results confirm the influence of presentation features on text quality rating. They encourage teachers to be aware of this effect and emphasize the importance of spelling and writing support and interventions for students with dyslexia throughout education.

Code Recommendation for Schema Evolution of Mimic Storage Systems

Schema evolution of mimic storage systems is a time-consuming and error-prone task due to the redundant development of heterogeneous executors. The ORM-based proxy requires an entire class to represent the structure of a data table. There lacks domain-specific code recommendation techniques to boost storage development. To address this issue, we design a novel type of code context, i.e. schema context, that combines features of code text, syntax and structure. Regarding the requirements of class-level granularity, we focus on behavior and attribute in code syntax, and use element position and structural metrics to mine the hidden relationships. Based on schema context and an existing inference mode, we propose SchemaRec to recommend ORM-related class for the database executors once one of them has been changed. We conduct experiments with 110 open-source projects, and the results show that SchemaRec obtains more accurate results than Lucene, DeepCS, QobCS and SEA in terms of Top-1, Top-10 and MRR accuracy due to the better ability of context representation. We also find that code syntax is the most important information because it involves behavior and attribute information of ORM-related classes.

Language Development Opportunities in Curricular and Trade Books: A Content Analysis

ABSTRACTThis content analysis explored children's fictional storybooks and informational science books to determine their differences in high‐quality text features that support oral language (OL) development. We also explored the opportunities for OL development in curricular books compared to trade books. Using systematic coding procedures, we evaluated the genre, vocabulary, syntactic variety, supportive visuals and cultural sensitivity in books from three kindergarten and Grade 1 reading curricula (n = 521) as well as a sample of commercially‐available trade books (n = 48). Descriptive information was averaged to determine the percentage of high‐quality text features included in each book type and genre. Results indicated that informational science trade books offered more opportunities for rich language experiences than their curricular counterparts or any of the fictional books. Thus, there is reason to believe that informational science trade books with high‐quality text features may promote OL development and enhance the learning of young students.

Text-Enhanced Graph Attention Hashing for Cross-Modal Retrieval

Deep hashing technology, known for its low-cost storage and rapid retrieval, has become a focal point in cross-modal retrieval research as multimodal data continue to grow. However, existing supervised methods often overlook noisy labels and multiscale features in different modal datasets, leading to higher information entropy in the generated hash codes and features, which reduces retrieval performance. The variation in text annotation information across datasets further increases the information entropy during text feature extraction, resulting in suboptimal outcomes. Consequently, reducing the information entropy in text feature extraction, supplementing text feature information, and enhancing the retrieval efficiency of large-scale media data are critical challenges in cross-modal retrieval research. To tackle these, this paper introduces the Text-Enhanced Graph Attention Hashing for Cross-Modal Retrieval (TEGAH) framework. TEGAH incorporates a deep text feature extraction network and a multiscale label region fusion network to minimize information entropy and optimize feature extraction. Additionally, a Graph-Attention-based modal feature fusion network is designed to efficiently integrate multimodal information, enhance the affinity of the network for different modes, and retain more semantic information. Extensive experiments on three multilabel datasets demonstrate that the TEGAH framework significantly outperforms state-of-the-art cross-modal hashing methods.

Roaming Pauses in Cormac McCarthy’s The Road

ABSTRACT This article discusses a textual feature in Cormac McCarthy’s novel The Road (2006) that has hitherto been misunderstood by the reception, namely the spaced ellipses between several paragraphs which are considered by notable McCarthy scholars to signal particularly distinct pauses in the textual flow of the novel. The article demonstrates that this is a misperception with significant consequences for the interpretation of the story’s rhythm. Drawing on textual scholars such as Jerome McGann, Bill Brown, John Bryant, and John B. Thompson, the article finally discusses how neutral bibliographical codes occasionally express their own intentions that are in conflict with those of the author.

Enhancing Multimodal Emotional Information Extraction in Film and Television through Adaptive Feature Fusion with DenseNe, Transformer, and 3D CNN Models

ABSTRACT The extraction of multimodal emotional information enables a more nuanced representation of the emotional subtleties embedded in film and television works. However, conventional approaches that independently extract features from images and text fail to capture the rich semantic interplay between these modalities, impeding the feature learning process within each modality. To address this, this paper presents an innovative model for extracting emotional information from multimodal film and television content. The model utilizes DenseNe for image feature extraction, enhancing network depth via the MSC module. Text feature extraction is achieved through a Transformer encoder, while video feature extraction employs a 3D CNN model. Refinements are made to the number and placement of convolutional layers, planar convolution size, and 3D convolution depth. Moreover, a multi-head scaled dot-product attention mechanism is incorporated into the interaction module to compute the similarity between each image block within the sequence and every word in the text sequence. Experimental evaluations on the CMU-MOSEI and CMU-MOSI datasets showcase superior performance compared to the baseline model, achieving accuracy and F1 scores of 0.708 and 0.698, respectively. Noteworthy is the proposed adaptive feature fusion module, which enriches the expressiveness of pivotal emotional features while eliminating redundant data.

Continuation and Chronography: Notes on the Composition of Ibn Aʿtham al-Kūfī’s History

Abstract This paper revisits the hypothesis that Ibn Aʿtham al-Kūfī (d. ca. 320/932) only wrote parts of the two works typically ascribed to him, the Kitāb al-Futūḥ and the Kitāb al-Taʾrīkh. Drawing on recent work that dates Ibn Aʿtham and his history to the first half of the fourth/tenth century, it seeks to demonstrate that textual features and narratives which have been interpreted as pointing toward a change in authorship need to be reconsidered. Ultimately, it is suggested that Ibn Aʿtham’s history, which has often been treated as an eccentric, possibly sectarian text, may be seen as more-or-less typical of fourth/tenth century historiography.

A Study of Fang Huawen’s Chinese Version of Rebecca from the Perspective of Skopos Theory

This paper analyzes Fang Huawen’s Chinese version of Rebecca from the perspective of Skopos Theory. By obtaining the different descriptions in the novel, such as linguistic description, mental description, and environmental description, the essay focuses on discovering how the translator uses Skopos Theory during his translation. Through the analysis, the thesis finds out that Fang’s version combines the features of the original texts and the expression habit in Chinese, which fully demonstrates the original texts. The language of Fang’s version is brief and clear, and the content is coherent, meanwhile, this translation showcases the message from the original text to a great extent. Through studying Fang’s version, the thesis analyzes the translation strategies comprehensively by using the principle of fidelity, conference and skopos. Based on the above three principles, translators can adopt a variety of translation strategies, including domestication, foreignization, addition and subtraction, to translate high-quality translations to meet the needs of readers and disseminate the culture of other countries.

A Method for Measuring Word Sequence Complexity of Text

ABSTRACT In linguistics and natural language processing, measuring text features is crucial for representing and revealing the properties of texts in terms of topics, genres, sentiment and more. Current methods predominantly rely on the frequency of linguistic units and rarely consider the syntagmatic properties of these units, which can reflect deeper linguistic characteristics (e.g. syntax and pragmatics). This paper proposes a general method for calculating the sequence complexity of text. By combining the features of word length and word frequency, two specific implementations of this method are provided. Using these two formulas, word sequence complexity of text based on the Brown Corpus and the Gutenberg Corpus is calculated. The results show that word sequence complexity of text indicates a characteristic of gradual stabilization. By comparing random texts with natural texts, it is found that word sequence complexity is influenced by syntactic rules rather than sentence order, and natural texts tend to alternate between words of varying lengths and frequencies. Classification experiment results indicate that the proposed word sequence complexity outperforms commonly used quantitative indicators for representing the genre of text, such as TTR, information entropy, Zipf’s law parameters and motifs.

Sentiment Analysis of Chinese Ancient Poetry Based on Multidimensional Attention Under the Background of Digital Intelligence Integration

Abstract Poetry was a unique literary genre in ancient China as an important way to express sentiments. Chinese ancient poetry not only has simple words, strict meters and rich semantic relationships, but also widely uses rhetorical techniques such as simile and personification, as well as metaphorical means such as allusion and imagery, which makes it difficult to understand their implicit sentiments quickly and accurately. Therefore, this paper attempts to make full use of the semantic features of Chinese ancient poetry text and the knowledge feature of related domains under the guidance of the research paradigm of digital intelligence integration, and based on which, proposed Sentiment Analysis Model of Chinese Ancient Poetry based on Multidimensional Attention (SAMCAP). This model extracts semantic features from Chinese ancient poetry text, meanwhile designs a multidimensional attention to extract the knowledge feature from the knowledge base of Chinese ancient poetry. The recognition of Chinese ancient poetry sentiment is performed by integrating the textual feature and knowledge feature. Comparison experiments on the open ancient poetry corpus verified the effectiveness of the proposed model, and the ablation experiment explored the importance of different knowledge to the sentiment analysis result of Chinese ancient poetry.

An Analysis of Traditional and Contemporary Children’s Songs With Considerations for Music Therapy Practice

Abstract Children’s songs include a diverse collection of traditional and contemporary songs. (Yinger and Springer [2016]. Analyzing recommended songs for older adult populations through linguistic and musical inquiry. Music Therapy Perspectives 34, 116–125. https://doi.org/10.1093/mtp/miu048) analyzed musical and textual features of songs used by music therapists with older adults; however, studies on children’s songs in music therapy have not included musical and textual features analysis. Our purpose with this study was to analyze the musical and textual features of a sample of 20 traditional and 20 contemporary predominantly U.S. children’s songs and consider applications for music therapy. Text information was collected, including total and unique words, the song topic, and potential applications. Musical information was collected, including form, melodic range, and harmonic/chordal structure. Findings included that the traditional songs were strophic, had fewer overall words, were harmonized with three chords or fewer, and had melodic ranges of five to seven notes. By contrast, contemporary children’s songs used complex song forms, had more words, were harmonized with more than three chords, and had melodic ranges of eight or more notes. Song topics and applications had similar codes across the song types. A music therapist may apply traditional songs in clinical work, where a simpler musical structure and fewer words support the client’s needs. Likewise, a music therapist may apply contemporary songs for greater musical complexity and more vocabulary. Future studies of children’s songs in music therapy could include an analysis of music therapists’ composed songs and songs used by music therapists who work with young children.

Cap2Seg: leveraging caption generation for enhanced segmentation of COVID-19 medical images

Incorporating medical text annotations compensates for the quality deficiencies of image data, effectively overcoming the limitations of medical image segmentation. Many existing approaches achieve high-quality segmentation results by integrating text into the image modality. However, these approaches require matched image-text pairs during inference to maintain their performance, and the absence of corresponding text annotations results in degraded model performance. Additionally, these methods often assume that the input text annotations are ideal, overlooking the impact of poor-quality text on model performance in practical scenarios. To address these issues, we propose a novel generative medical image segmentation model, Cap2Seg (Leveraging Caption Generation for Enhanced Segmentation of COVID-19 Medical Images). Cap2Seg not only segments lesion areas but also generates related medical text descriptions, guiding the segmentation process. This design enables the model to perform optimal segmentation without requiring text input during inference. To mitigate the impact of inaccurate text on model performance, we consider the consistency between generated textual features and visual features and introduce the Scale-aware Textual Attention Module (SATaM), which reduces the model’s dependency on irrelevant or misleading text information. Subsequently, we design a word-pixel fusion decoding mechanism that effectively integrates textual features into visual features, ensuring that the text information effectively supplements and enhances the image segmentation task. Extensive experiments on two public datasets, MosMedData+ and QaTa-COV19, demonstrate that our method outperforms the current state-of-the-art models under the same conditions. Additionally, ablation studies have been conducted to demonstrate the effectiveness of each proposed module. The code is available at https://github.com/AllenZzzzzzzz/Cap2Seg.

DPNet: Scene text detection based on dual perspective CNN-transformer.

With the continuous advancement of deep learning, research in scene text detection has evolved significantly. However, complex backgrounds and various text forms complicate the task of detecting text from images. CNN is a deep learning algorithm that automatically extracts features through convolution operation. In the task of scene text detection, it can capture local text features in images, but it lacks global attributes. In recent years, inspired by the application of transformers in the field of computer vision, it can capture the global information of images and describe them intuitively. Therefore, this paper proposes scene text detection based on dual perspective CNN-transformer. The channel enhanced self-attention module (CESAM) and spatial enhanced self-attention module (SESAM) proposed in this paper are integrated into the traditional ResNet backbone network. This integration effectively facilitates the learning of global contextual information and positional relationships of text, thereby alleviating the challenge of detecting small target text. Furthermore, this paper introduces a feature decoder designed to refine the effective text information within the feature map and enhance the perception of detailed information. Experiments show that the method proposed in this paper significantly improves the robustness of the model for different types of text detection. Compared to the baseline, it achieves performance improvements of 2.51% (83.81 vs. 81.3) on the Total-Text dataset, 1.87% (86.07 vs. 84.2) on the ICDAR 2015 dataset, and 3.63% (86.72 vs. 83.09) on the MSRA-TD500 dataset, while also demonstrating better visual effects.

Core-Periphery Multi-Modality Feature Alignment for Zero-Shot Medical Image Analysis.

Multi-modality learning, exemplified by the language-image pair pre-trained CLIP model, has demonstrated remarkable performance in enhancing zero-shot capabilities and has gained significant attention recently. However, simply applying language-image pre-trained CLIP to medical image analysis encounters substantial domain shifts, resulting in severe performance degradation due to inherent disparities between natural (non-medical) and medical image characteristics. To address this challenge and uphold or even enhance CLIP's zero-shot capability in medical image analysis, we develop a novel approach, Core-Periphery feature alignment for CLIP (CP-CLIP), to model medical images and corresponding clinical text jointly. To achieve this, we design an auxiliary neural network whose structure is organized by the core-periphery (CP) principle. This auxiliary CP network not only aligns medical image and text features into a unified latent space more efficiently but also ensures alignment driven by principles of brain network organization. In this way, our approach effectively mitigates and further enhances CLIP's zero-shot performance in medical image analysis. More importantly, the proposed CP-CLIP exhibits excellent explanatory capability, enabling the automatic identification of critical disease-related regions in clinical analysis. Extensive experiments and evaluation across five public datasets covering different diseases underscore the superiority of our CP-CLIP in zero-shot medical image prediction and critical features detection, showing its promising utility in multimodal feature alignment in current medical applications.

A multi-level text feature enhancement super-resolution network via group convolution and wavelet transform

A multi-level text feature enhancement super-resolution network via group convolution and wavelet transform

Reality Show in the context of “Post-Documentary” Culture: Critics of Textual Approach

The purpose of the article is to review important aspects of the critical studies in foreign scientific discourse aimed at textual analysis of reality show as a genre and television format, which helps to reconsider its status as a phenomenon of “post-documentary” culture. The research methodology. The work uses, firstly, critical discourse analysis, which allows us to understand the limitations and counterproductiveness of textual analysis of reality show and helps to reveal the constitutive potential of television and cultural production practices, and, secondly, a cultural approach, which allowed us to identify the media-cultural features of reality show and show them as an element of “post-documentary” audio-visual culture in the XXI century. Scientific novelty of the research lies in the fact that for the first time, through the prism of criticism of the textual approach, the peculiarities of reality show as a phenomenon of “post-documentary” audio-visual culture are revealed. Conclusions. It is proved that the counterproductiveness of the textual approach to the conceptualisation of reality show as a genre, since its production contradicts the general logic and the established perception of what a text should be. This genreform has more common with no certain genre traditions or textual features, but with the “processing of reality” at the intersection of fact and fiction, shifting attention from the text to its production. The proliferation of reality TV programmes illustrates the industry’s dependence on “reality” as a tool for advertising marketing and the logic of cultural production. It is affirmed that during conceptualising TV reality texts, it is necessary to pay attention to a number of industrial and market conditions and needs, which prioritises textual production practices and contexts that shape practical decisions, and allows for empirical access to the evolving and mutating genreform of reality show.

The influence of UGC features on consumers' purchase intention in social e-commerce platforms: Taking Xiaohongshu as an example

With the rapid development of social e-commerce, content-based social e-commerce platforms have become one of the main channels for consumers to obtain information. And this social e-commerce platform relies on user generated content to convey valuable information to users. The relationship between user generated content and user purchase intention is still a question worth exploring. This article starts from an empirical perspective and studies the mediating variables between UGC text features and consumer purchase intention in social e-commerce platforms. Based on speech act theory (SAT) and receptor stimulus response theory (SOR), research hypotheses are proposed, with perceived value, perceived risk, and perceived interest as mediating variables. By using AMOS to construct a structural effects equation for verification, it is concluded that UGC text features can positively affect perceived value, perceived risk, perceived interest, and have an effective impact on purchase intention.

A text sentiment analysis method based on BiGRU and capsule network

Most of the existing sentiment analysis methods based on product review texts rarely consider the aspect features of the review texts, and the relevant analysis models do not consider the long-term contextual dependency features and local text features at the same time, thus affecting the accuracy of sentiment analysis. A text sentiment analysis method based on a bidirectional gated recurrent network (BiGRU) and a capsule network is proposed. This method first uses a word frequency statistics-based method to extract the aspect features of the review text and integrates them into the word vector representation, thereby effectively improving the expressive power of the word vector. Then, BiGRU is used to extract the long-term contextual dependency features of the text, and the capsule network is used to extract the local features of the text, thereby achieving high-precision text sentiment analysis based on aspects. Experimental results on real datasets show that the proposed method is superior to existing sentiment analysis models such as bidirectional long short-term memory network (BiLSTM), CNN-LSTM, and TextCNN in terms of evaluation indicators such as accuracy, precision, recall, and score.

A Label Information Aware Model for Multi-label Text Classification

Multi-label text classification (MLTC) refers to that each document is associated with more than one label at the same time, which attract much attention from researchers in both academia and industry. Existing methods have difficulties in determining label-related components from documents, which cannot effectively establish the association between textual features and label information. In fact, there are some label information, such as label semantic information and co-occurrence relations among labels, could be used to improve the performance on multi-label text classification. In this paper, we propose a label information aware model to utilize these information. Our model makes use of label semantic information to determine label-related components from textual features for obtaining the label-specific textual presentation for each sample, and then take advantages of co-occurrence relations among labels to construct interaction among label-specific textual presentation. The superiority of our model has been proved through comparing our method with several existing models on two datasets.

Comic timing in prose fiction

Abstract This article explores the perception of comic timing effects in prose fiction and the involvement of this effect in a reader’s ability to recognise and appreciate humour. It suggests that the effect of comic timing, generally, results from perceived changes in pace rather than absolute timing. In a written text, a comic timing effect can be constructed linguistically through changes in perceived narrative urgency. In the passages analysed here, this change is from a state of impeded urgency, where textual features that encourage a sense of pace are combined with features that diminish this, to a state where the impediment to urgency is removed. This corresponds with and contributes to the reader’s sense of emergence from the text world, a positional shift that encourages their sense of sharing humour with the author.