Non-text Elements Research Articles

Sentiment Classification of User Reviews for KAI Access Application Using Naive Bayes Method

KAI Access is a train ticket booking application that offers convenience and various features for its users. However, the app has received a low rating of 2.4 out of 5 stars on the Play Store, indicating user dissatisfaction. This study conducts a quantitative sentiment analysis of the KAI Access application based on user sentiments expressed on Twitter. Using the CRISP-DM method, data were collected from Twitter with the Tweepy tool, amassing around 4,000 tweets from June to August 2023. The data underwent a preprocessing stage to ensure the quality and accuracy of the analysis. This stage involved removing duplicate tweets, eliminating retweets, and filtering out emoticons and other non-text elements. In the modeling stage, the Multinomial Naive Bayes Classifier algorithm was employed, achieving an accuracy rate of 84.6%. The model performed better at identifying negative reviews, with a precision of 0.96, recall of 0.86, and an F1-score of 0.91. In contrast, the identification of positive reviews was less effective, with a precision of 0.41, recall of 0.75, and an F1-score of 0.53. These findings shed light on the low ratings for KAI Access, particularly in the context of user reviews. The results of this study provide further understanding regarding the low rating given to KAI Access, particularly in the context of user reviews. By using this classification system, it is hoped that developers can design more specific improvements to enhance the user experience, especially in handling positive reviews which have the potential for performance improvement.

UI semantic component group detection: Grouping UI elements with similar semantics in mobile graphical user interface

Texts, widgets, and images on a UI page do not work separately. Instead, they are partitioned into groups to achieve certain interaction functions or visual information. Existing studies on UI elements grouping mainly focus on a specific single UI-related software engineering task, and their groups vary in appearance and function. In this case, we propose our semantic component groups that pack adjacent text and non-text elements with similar semantics. In contrast to those task-oriented grouping methods, our semantic component group can be adopted for multiple UI-related software tasks, such as retrieving UI perceptual groups, improving code structure for automatic UI-to-code generation, and generating accessibility data for screen readers. To recognize semantic component groups on a UI page, we propose a robust, deep learning-based vision detector, UISCGD, which extends the SOTA deformable-DETR by incorporating UI element color representation and a learned prior on group distribution. The model is trained on our UI screenshots dataset of 1988 mobile GUIs from more than 200 apps in both iOS and Android platforms. The evaluation shows that our UISCGD achieves 6.1% better than the best baseline algorithm and 5.4 % better than deformable-DETR in which it is based.

Modernist Literary-Criticism in Indonesia: A Study on the Practices of Millenial Digital Literacy on the Youtube Comments

The research was focused on investigating the tradition of modernist literary criticism, which could be found in the audience’s comments under the video on the YouTube website. As the center of the digital literary paradigm, digital poetry in videography has become an object of criticism for the Indonesian millennial generation. As was known, one of the markers of digital literacy was proficiency in using digital media. One of these media was used to produce criticism by voicing non-text semiotics. Because of that, in the research, thousands of criticisms that appeared on the poetry websites “Aksara Betha” and “Rotasi” were analyzed by reviewing examples of the critics’ expressions of non-text elements that could be found in the constructs of the two digital poetry. The results show that Indonesian millennials are digitally literate, and many explicitly mention digital art features that have attracted their interest. Some critics even express their subjective feelings about the show’s duration which is considered too short. Such practice explains that the Indonesian millennial generation has felt the effect of one of the morphological elements of digital poetry, namely space and time. Furthermore, suppose it can be called a tradition; in that case, the honesty of the critics in collecting criticism of the work they prepare is the milestone of the new tradition in literary criticism. This tradition is rarely, if not never, to be found in the tradition of printed literary criticism.

DupHunter: Detecting Duplicate Pull Requests in Fork-Based Development

The emergence of numerous fork-based development platforms facilitates the development of Open-Source Software (OSS) projects. Developers across the world can fork software projects and submit their Pull Requests (PRs) to the projects. However, as the number of forks increases, numerous duplicate PRs might be submitted. These duplicate PRs may cause extra code review workload and frustrate developers working on the projects. To detect duplicate PRs, many approaches have been proposed, which analyze the similarity of different elements in PRs. However, previous approaches still suffer from unsatisfied detection accuracy due to two challenges. That is, they ignore the syntactic structural information of text elements in PRs and lack the joint reasoning between different elements of two PRs. In this study, we propose an automated duplicate PRs detector named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DupHunter</i> ( <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Dup</b> licate PRs <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Hunter</i> ), which includes a graph embedding component and a duplicate PRs detection component to address the above challenges. The graph embedding component uses a feature graph to represent a PR. It encodes the syntactic structure and semantics of text elements (e.g., the title and the description), as well as the knowledge of non-text elements (e.g., the submission time), to address the syntactic structural information challenge. The duplicate PRs detection component tackles the joint reasoning challenge using a graph matching network, which enables the information exchange and matching across different elements of two feature graphs with an attention coefficient mechanism. Experiments on 26 open-source projects show that DupHunter achieves an average <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F1-score@1</i> value of 0.650, significantly outperforming the state-of-the-art approaches by 3.2% to 48.1%. DupHunter can accurately detect duplicate PRs, with an average <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Precision@1</i> value of 0.922 and an average <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Recall@1</i> value of 0.502.

Analysis of Online Accessibility of Public Access Catalogue on Slims and Inlislite Applications Based on WCAG 2.0

This study aims to determine the level of OPAC accessibility in SLiMS and INLISLite applications. Four main guidelines on website accessibility will be analyzed: perceivable, operable, adaptable, and robust. The four guidelines are based on the Web Content Accessibility Guidelines (WCAG). This study uses a quantitative approach with descriptive methods and data analysis techniques using manual checks based on the WCAG-EM guidelines, which focus on two levels, namely A and AA. The results of the study based on four indicators are (1) perceivable on SLiMS and INLISLite experiencing problems in providing alternative text, (2) operable on SLiMS and INLISLite found problems in the focus element, (3) understandable on SLiMS and INLISLite fail to meet the criteria for providing language, and (4) robust, both applications have succeeded in utilizing HTML syntax according to the provisions. Thus, from the four indicators, the SLiMS and INLISLite applications still need to meet several criteria at level A, namely the criteria for using language, using color, and providing alternative text on non-text elements. Meanwhile, at level AA, there is a failure in the focus element.

A Novel Method for Image to Text Extraction Using Tesseract-OCR

Text extraction process can play a vital role for detecting valuable information from a selected image. This text extraction process involves text detection, localization, marking, tracking, extraction, enhancement and finally recognition task. It is a difficult task to detect these text characters, because of their variation of size, style, font, orientation, alignment, contrast, color and textured background. There is a growing demand of information detection, indexing and retrieval from various multimedia documents nowadays. Several methods have been developed for extraction of text from an image. This article proposes a novel method for image to text extraction. In this paper, we are presenting a multiresolution morphology based text segmentation process suitable for various types of non-text elements like drawing, pictures, halftones or etc. For image processing, python library OpenCV is used and for text extraction Tessaract is used. Python Imaging Library (PIL) is capable to handle the opening and manipulation of images in many formats in Python. Also we are in testing of such an application that can give output in every language correctly.

Archive Card Index vs. Transkribus: machine recognition of handwritten text

The subject of the research is machine recognition of handwritten materials of the Archival Card Index (ACI) — lexical and phraseological materials of the dictionary commission of the All-Ukrainian Academy of Sciences, in particular, card index of the “Russian-Ukrainian dictionary” 1924–1933 ed. A. Krymsky and S. Yefremov. The study of the ACI should be considered in the context of cultural and national revival in Ukraine in the 20th — early 21st centuries. The relevance and value of the ACI became a prerequisite for the transfer of its materials to the digital format. In 2018 the Institute of Ukrainian Language of the NAS of Ukraine created a computer system “Archival Card Index”, which accessibles materials primarily in the form of scanned images. The problem that needs urgent resolution is the transfer of handwriting to a typewriter format. The complexity of manual recognition, which requires considerable effort and time, encourages the study and application of Transkribus resource capabilities, which involves the use of the machine teaching. The Aim of the study is to clarify by analyzing, systematizing, classifying and describing the material features of the preparation of ACI cards for machine processing of texts. The scientific novelty of the study is that for the first time, the issue of providing the HTR engine with ACI training data (loading to the platform, segmenting images into lines and text areas, transcribing content each page). The main result is finding out the content of the preparatory stage, the tasks of which are to eliminate the flaws of automatic segmentation: non-text elements, non-substantial text elements, incorrect automatic detection of text region or line. The prospects of lexicographic toloka (crowdsourcing) in the process of card recognition are outlined, for which it is envisaged to use collective access to the collection of transcribed documents in Transkribus. To recognize the cards manually and for the future check and adjustment of automatically recognized ones, you can join the new project “All-Ukrainian Toloka: Archival Card Index” — online platform on the website “ACI”.

Accessible images (AIMS): a model to build self-describing images for assisting screen reader users

Non-visual web access depends on the textual description of various non-text elements of web pages. The existing methods of describing images for non-visual access do not provide a strong coupling between described images and their description. If an image is reused multiple times either in a single Web site or across multiple times, it is required to keep the description at all instances. This paper presents a tightly coupled model termed accessible images (AIMS) which utilizes a steganography-based approach to embed the description in the images at the server side and updating alt text of the web pages with the description extracted with the help of a browser extension. The proposed AIMS model has been built, targeting toward a web image description ecosystem in which images evolve into a self-description phase. The primary advantage of the proposed AIMS model is the elimination of the redundant description of an image resource at multiple instances. The experiments conducted on a dataset confirm that the AIMS model is capable of embedding and extracting descriptions with an accuracy level of 99.6%.

The extraction method of new logining word/term for social media based on statistics and N-increment

New logining word/terms are reasonably extracted to improve the accuracy of information retrieval and to provide the theoretical support for tracking network topics and social public opinion. To efficiently mine new logining word/terms from micro-blog, this paper presents an extraction method of new logining word/term for social media based on statistics and N-increment. First, some words with very high frequency occurring in micro-blog text, called as similar stop-words, are collected into a list according to abuttal entropy. Second, micro-blog text is preprocessed by deleting similar stop-words and non-text elements. And then the preprocessed micro-blog text is scanned to extract new logining word/term according to N-increment and internal statistics. The experimental results show that the proposed algorithm can accurately and quickly extract micro-blog new logining word/term.

A mixture model using Random Rotation Bounding Box to detect table region in document image

Table detection in the document image is still a challenging problem due to the variety of table structures and the complexity of document layout. In this paper, we propose a novel method for detecting table regions by using a new shape which is called Random Rotation Bounding Box. This shape is used for illustration and description of the table regions. Based on it, our system performs the following three fundamental steps to detect the table zones: classification of the text and non-text elements in the document image, detection of the ruling-line tables, and identification of the non-ruling-line tables. Different from other methods, our approach can detect most kinds of tables with high precision even when it is skewed. Besides, the proposed method is also designed to fit in the document layout analysis system. Our algorithm has been tested on the two well-known, and a commercial datasets: ICDAR2013 table competition, UNLV, and Diotek. Experimental results on these databases show that our method is more robust and efficient than previous systems.

Page segmentation using minimum homogeneity algorithm and adaptive mathematical morphology

Document layout analysis or page segmentation is the task of decomposing document images into many different regions such as texts, images, separators, and tables. It is still a challenging problem due to the variety of document layouts. In this paper, we propose a novel hybrid method, which includes three main stages to deal with this problem. In the first stage, the text and non-text elements are classified by using minimum homogeneity algorithm. This method is the combination of connected component analysis and multilevel homogeneity structure. Then, in the second stage, a new homogeneity structure is combined with an adaptive mathematical morphology in the text document to get a set of text regions. Besides, on the non-text document, further classification of non-text elements is applied to get separator regions, table regions, image regions, etc. The final stage, in refinement region and noise detection process, all regions both in the text document and non-text document are refined to eliminate noises and get the geometric layout of each region. The proposed method has been tested with the dataset of ICDAR2009 page segmentation competition and many other databases with different languages. The results of these tests showed that our proposed method achieves a higher accuracy compared to other methods. This proves the effectiveness and superiority of our method.

Separation of Text and Non-text in Document Layout Analysis using a Recursive Filter

A separation of text and non-text elements plays an important role in document layout analysis. A number of approaches have been proposed but the quality of separation result is still limited due to the complex of the document layout. In this paper, we present an efficient method for the classification of text and non-text components in document image. It is the combination of whitespace analysis with multi-layer homogeneous regions which called recursive filter. Firstly, the input binary document is analyzed by connected components analysis and whitespace extraction. Secondly, a heuristic filter is applied to identify non-text components. After that, using statistical method, we implement the recursive filter on multi-layer homogeneous regions to identify all text and non-text elements of the binary image. Finally, all regions will be reshaped and remove noise to get the text document and non-text document. Experimental results on the ICDAR2009 page segmentation competition dataset and other datasets prove the effectiveness and superiority of proposed method.

'The kind of mildly curious sort of science interested person like me': Science bloggers' practices relating to audience recruitment.

With at least 150 million professional and amateur blogs on the Internet, blogging offers a potentially powerful tool for engaging large and diverse audiences with science. This article investigates science blogging practices to uncover key trends, including bloggers’ self-perceptions of their role. Interviews with seven of the most popular science bloggers revealed them to be driven by intrinsic personal motivations. Wishing to pursue their love of writing and share their passion for science, they produce content suitable for niche audiences of science enthusiasts, although they do not assume background scientific knowledge. A content analysis of 1000 blog posts and comparison with the most popular blogs on the Internet further confirmed this result and additionally identified key factors that affect science blog popularity, including update frequency, topic diversity and the inclusion of non-text elements (especially images and video).

Extended Approach to Water Flow Algorithm for Text Line Segmentation

This paper proposes a new approach to the water ∞ow algorithm for text line segmentation. In the basic method the hypothetical water ∞ows under few specifled angles which have been deflned by water ∞ow angle as parameter. It is applied to the document image frame from left to right and vice versa. As a result, the unwetted and wetted areas are established. These areas separate text from non-text elements in each text line, respectively. Hence, they represent the control areas that are of major importance for text line segmentation. Primarily, an extended approach means extraction of the connected-components by bounding boxes over text. By this way, each connected component is mutually separated. Hence, the water ∞ow angle, which deflnes the unwetted areas, is determined adaptively. By choosing appropriate water ∞ow angle, the unwetted areas are lengthening which leads to the better text line segmentation. Results of this approach are encouraging due to the text line segmentation improvement which is the most challenging step in document image processing.

Using Shape and Layout Information to Find Signatures, Text, and Graphics

The decomposition of a page image into text and various types of nontext elements is a challenging problem important in document analysis problems such as optical character recognition, storage and retrieval, and identification of the sender and recipient of a FAX. A fast classifier based on a skeletonization of the image attempts to classify groups of related line segments as text, ruling lines, signatures, other line art, or miscellaneous items. Then everything classified as text is processed by Baird's language-free layout analysis system so that a postprocessor can use the geometric layout to refine decisions about what is text and what is nontext. This could then be further processed to identify complex objects such as tables, signature blocks, and line drawings. In order to recognize signatures and to separate them from ruling lines and components of line drawings, line segments from skeletonization need to be strung together by a curve-fitting process. After long, fairly straight lines are found and set aside, a more lenient criterion strings together pairs of segments to form the groups on which to run the fast classifier.

Text extraction from colored book and journal covers

Abstract. The automatic retrieval of indexing information from colored paper documents is a challenging problem. In order to build up bibliographic databases, editing by humans is usually necessary to provide information about title, authors and keywords. For automating the indexing process, the identification of text elements is essential. In this article an approach to automatic text extraction from colored book and journal covers is proposed. Two methods have been developed for extracting text hypotheses. The results of both methods are combined to robustly distinguish between text and non-text elements.