Text Technologies Process Research Articles

Unlocking Insights: A Literature Review on Enhanced Confix Stripping and Nazief & Adriani Algorithm Modifications for Makassar Language Text Stemming

This study investigates the Nazief and Adriani Algorithm and the Enhanced Confix Stripping Stemmer (ECS) in the context of Makassar language. Following a comprehensive investigation, the Nazief & Adriani Algorithm demonstrates proficiency in capturing the complexities of Makassar language by applying numerous morphological criteria. Meanwhile, the Enhanced Confix Stripping Stemmer (ECS) exhibits versatility in dealing with language obstacles, identifying opportunities for further improvement. Using Sastrawi, Confix Stripping, Enhanced Confix Stripping, and Nazief-Adriani, the study emphasizes the need of using linguistically suitable techniques for exact analysis. This work sheds light on improving text processing technology in Makassar language, opening the path for algorithms customized to the language's unique qualities.

Visual Communication Design Method Based on Multimedia Information Processing Technology and Its Application

Abstract When the information society has become the mainstream environment, various applications of big data and computers have been popularized in various industries. Multimedia technology has always been a special part of the computer field. In audio, video, image processing, and transmission, multimedia information processing has become the main means to solve the above problems. The performance of this information processing technology is extremely powerful. It can not only process dynamic data but also complete the transmission task in the big data environment. Visual communication design is a way of transmitting information to the masses by using various effects, and it has its advantages in the selection of images, video, text, and other processing technologies. This paper mainly studies the concept, method, and application effect of visual communication design under multimedia information processing. Firstly, the application of multimedia information processing technology in various fields and countries is investigated. Based on the literature analysis and statistics, the advantage tendency of this technology is judged. Starting from the visual functions involved in visual communication, the application effect of the multimedia 3D image processing and rendering communication platform is used. The gray function is used to build the multimedia information processing platform and form a complete and effective evaluation system. Finally, the visual communication design optimized by multimedia processing technology is further analyzed to improve the defects of dynamic images in visual applications and further improve the impact of visual communication design on the masses. The results show that multimedia information processing technology can improve the efficiency of image data processing in visual communication design, and has a good impact on visual communication of dynamic information.

Collection of Road Traffic Incidents in Bangkok from Twitter Data based on Deep Learning Algorithm

Text processing technology from Twitter to report notification formats that are known in many countries with verification on different languages. This research presents the development of a neural network memory learning model. To solve the problem of classifying incidence patterns and identifying severity of incidents from Thai social media messages. For gathering incident data and reporting incidents externally from a single reporting platform by using deep learning models like MLP, CNN and LSTM which is designed by dividing the study into 3 types, including examination traffic incidence identification pattern that can identify the report as general news or traffic reporting Incident Identification Patterns. These include traffic conditions, accidents, disasters, damaged roads, or other than the aforementioned patterns, and the pattern indicating the severity of the incidence consists of normal level, medium level and lane blocking or stationary levels. The results demonstrated the ability of LSTM learning with the best results in incidence detection and incidence pattern identification at 93.44% and 87.40%, respectively, and the CNN method was able to State the severity of the incidence at best, reaching 91.42%.

Collection of Road Traffic Incidents in Bangkok from Twitter Data based on Deep Learning Algorithm

Text processing technology from Twitter to report notification formats that are known in many countries with verification on different languages. This research presents the development of a neural network memory learning model. To solve the problem of classifying incidence patterns and identifying severity of incidents from Thai social media messages. For gathering incident data and reporting incidents externally from a single reporting platform by using deep learning models like MLP, CNN and LSTM which is designed by dividing the study into 3 types, including examination traffic incidence identification pattern that can identify the report as general news or traffic reporting Incident Identification Patterns. These include traffic conditions, accidents, disasters, damaged roads, or other than the aforementioned patterns, and the pattern indicating the severity of the incidence consists of normal level, medium level and lane blocking or stationary levels. The results demonstrated the ability of LSTM learning with the best results in incidence detection and incidence pattern identification at 93.44% and 87.40%, respectively, and the CNN method was able to State the severity of the incidence at best, reaching 91.42%.

International conference "Plagiarism Detection": does an academic journal need plagiarism checking?

This article presents the overview of the Vth and VIth annual International Scientific and Practical Conference "Plagiarism Detection" (hereinafter – the conference; website: ozconf.ru), held October, 2020 and 2021. The main aim of this major professional platform is to create expert environment for discussing plagiarism in the educational and scientific communities in the CIS countries, to inform about the novel text processing technologies, text mining and assessing its originality, as well as to discuss the use electronic resources in education and science to facilitate networking of specialists. The article reviews some definitions and presents examples of unethical behaviour in science, such as plagiarism, self-plagiarism, duplication (i.e. multiple publications), fraud and data fabrication. By using such practices some unscrupulous authors assign to themselves the credit of other scientists’ achievements and results, present out-dated results as new, perform data hacking and manipulate research process to obtain an anticipated result. Altogether such practice builds the illusion of promoting the knowledge and publication activity, providing the authors with access to financial support, salary increase, career promotion, bogus authority and standing in the science environment. The article also presents some law aspects concerning the authorship and plagiarism in the Russian academic community, reiterating that plagiarism is a criminal law category and can be regarded as a crime if it causes substantial damage to authors or copyright holders. Revealing errors, typos, plagiarism and other infringements of ethical norms and regulations in works, published by many journals and publishers, is comparable with eroding credibility and authority, as well as necessitating special checks, errata correction and possible retraction of publications. The situation, however, looks different if the victimized scientists consider compensation for the violation of the copyright and property ownership rights. The article lists examples and the main reasons for retracting fraudulent publications. The aim of retraction is to correct the information published, ensuring its validity, rather than to punish the authors. In the Russian research publishing environment publication retraction has been so far rather scarce. Yet globally the practice of retraction is rather widely spread. The article also summarizes the main features distinguishing unethical publishers, focusing on similarities and differences between journal-clones and journal-predators. It is estimated that currently there is information about hundreds of hijacked journals and more than one hundred thousand authors of the publications in journal-clones. The article also presents some information, pertaining to the history of “Antiplagiat” company establishment and its service development, drawing attention to different points of view about the need to use “Antiplagiat” system or other software for checking education and research publications for plagiarism. It is concluded that any search engines are not ideal and cannot substitute humans in crucial decision-making about a publication. Only an expert in the field, who can judge adequately about the exact substantive nature of text duplications and can assess adequately the scale of borrowing, shall make such decisions. Shifting responsibility from a human being to the “Antiplagiat” system by citing the rate of borrowings, provided by the system, is unethical practice as well.

SMS CLASSIFICATION: CONJOINT ANALYSIS OF MULTINOMIAL NAIVE BAYES APPLICATION

Nowadays there are ham and spam messages that are sent to the users via SMS. The aim of this article is to show how machine learning and text processing technologies can be used in order to predict the trustworthiness of SMS messages. The data we are going to use is collected from Kaggle. This study is very important because it helps us to understand how machine learning and text processing can be used in order to predict message trustworthiness. At the time of writing this article, there was not an article explaining how this can be done using the Multinomial Naive Bayes algorithm. The methodology we used in this article consists of dataset collection, data cleaning, data analysis, text preparation, and training model. This will be seen in the methodology section in great detail. At the end of this article, we will show to u the accuracy that we have got when implementing a Multinomial Naive Bayes algorithm for the classification of SMS messages. This study was quite beneficial because anyone can see how Multinomial Naive Bayes algorithm usage can be beneficial in order to predict the trustworthiness of SMS messages.

Research on the Importance of Data Enhancement Technology in Power Document Understanding

With the rise and development of the Internet and the artificial intelligence boom, natural language processing has been greatly developed in various fields and industries, including power industry. Intelligent document understanding, as a sub field of natural language understanding, uses artificial intelligence technology to enable machines to have natural language understanding ability. It has always been the focus of researchers and industry, and it is also the core problem of intelligent semantic interaction. As a common method to expand the sample set, data enhancement technology is an important text and image processing technology. Its core purpose is to use limited data and produce value equivalent to that from much more data. This technology has been widely used in various fields of deep learning. This paper reviews the development of data enhancement technology, lists and discusses five kinds of text enhancement technology paths and their corresponding representative technologies, including back translation, random word replacement, non core word replacement, text enhancement based on context information, and text enhancement technology based on generative language model. It also analyzes the effectiveness of text enhancement technology in the aspects of regularization, transfer learning, improving model robustness, manifold and so on, to achieve the goal of improving the accuracy and effectiveness of document understanding in power industry.

Negative emotion diffusion and intervention countermeasures of social networks based on deep learning

Aiming at the limitation of using only word features in traditional deep learning sentiment classification, this paper combines topic features with deep learning models to build a topic-fused deep learning sentiment classification model. The model can fuse topic features to obtain high-quality high-level text features. Experiments show that in binary sentiment classification, the highest classification accuracy of the model can reach more than 90%, which is higher than that of commonly used deep learning models. This paper focuses on the combination of deep neural networks and emerging text processing technologies, and improves and perfects them from two aspects of model architecture and training methods, and designs an efficient deep network sentiment analysis model. A CNN (Convolutional Neural Network) model based on polymorphism is proposed. The model constructs the CNN input matrix by combining the word vector information of the text, the emotion information of the words, and the position information of the words, and adjusts the importance of different feature information in the training process by means of weight control. The multi-objective sample data set is used to verify the effectiveness of the proposed model in the sentiment analysis task of related objects from the classification effect and training performance.

Asynchronous Speech Recognition Affects Physician Editing of Notes.

Clinician progress notes are an important record for care and communication, but there is a perception that electronic notes take too long to write and may not accurately reflect the patient encounter, threatening quality of care. Automatic speech recognition (ASR) has the potential to improve clinical documentation process; however, ASR inaccuracy and editing time are barriers to wider use. We hypothesized that automatic text processing technologies could decrease editing time and improve note quality. To inform the development of these technologies, we studied how physicians create clinical notes using ASR and analyzed note content that is revised or added during asynchronous editing. We analyzed a corpus of 649 dictated clinical notes from 9 physicians. Notes were dictated during rounds to portable devices, automatically transcribed, and edited later at the physician's convenience. Comparing ASR transcripts and the final edited notes, we identified the word sequences edited by physicians and categorized the edits by length and content. We found that 40% of the words in the final notes were added by physicians while editing: 6% corresponded to short edits associated with error correction and format changes, and 34% were associated with longer edits. Short error correction edits that affect note accuracy are estimated to be less than 3% of the words in the dictated notes. Longer edits primarily involved insertion of material associated with clinical data or assessment and plans. The longer edits improve note completeness; some could be handled with verbalized commands in dictation. Process interventions to reduce ASR documentation burden, whether related to technology or the dictation/editing workflow, should apply a portfolio of solutions to address all categories of required edits. Improved processes could reduce an important barrier to broader use of ASR by clinicians and improve note quality.

Application Holy Wars or a New Reformation: A Fugue on the Theory of Knowledge

Application Holy Wars or a New Reformation: A Fugue on the Theory of Knowledge

IPLR: an online resource for Greek word-level and sublexical information

We present a new online psycholinguistic resource for Greek based on analyses of written corpora combined with text processing technologies developed at the Institute for Language & Speech Processing (ILSP), Greece. The "ILSP PsychoLinguistic Resource" (IPLR) is a freely accessible service via a dedicated web page, at http://speech.ilsp.gr/iplr . IPLR provides analyses of user-submitted letter strings (words and nonwords) as well as frequency tables for important units and conditions such as syllables, bigrams, and neighbors, calculated over two word lists based on printed text corpora and their phonetic transcription. Online tools allow retrieval of words matching user-specified orthographic or phonetic patterns. All results and processing code (in the Python programming language) are freely available for noncommercial educational or research use.

Ontology based knowledge extraction for shipyard fabrication workshop reports

In this paper, a method to extract knowledge from a set of surveyors’ reports is proposed. Many surveyors from shipping companies are working in shipyards to improve the quality and to meet requirements of the ship owner. At present, the reports from surveyors are used only for managing the status of problems of the product. The proposed method here has three steps. First, the description field of the reports which contains information about some trouble is summarized in a pair of a component name and a trouble name in the failure database; this is made possible through text-processing technology. Second, synonymous component and trouble names are consolidated into normalized terms using synonym ontology to prepare this information for statistical analysis. The synonym ontology is developed prior to this procedure. The system evaluates frequent trouble records by classifying the records using component and process ontology. In the last step, the designers extract knowledge from the information generated by the system. The results illustrate common design problems, and the method is proved to be useful.

Automatic Categorization

ABSTRACT Automatic categorization is a new technology designed to control the flood of unstructured, non-indexed, and unorganized digital content that threatens to swamp knowledge workers in corporations and government. Auto-categorization software tools provide the means to categorize digital content according to predefined taxonomies, to extract concepts and entities for the development of taxonomies and to tag content with subject-related metadata tags.This paper describes the primary text-processing technologies employed by auto-categorization tools, outlines the features of the tools and discusses the human/machine interaction required to execute an effective categorization process. This paper is based on the contents of a presentation given at the Canadian Metadata Forum, Ottawa, September 26-28, 2005.

SuperNews: Multiple feeds for multiple views

The IBM intranet hosts a range of news “feeds,” or distribution services, from internal and external sources. To read the news of the day, users need to visit a number of Web sites, each with a different categorization, navigational structure, and layout. Transfer of technology from the MIT Media Laboratory to IBM enabled the design of SuperNews, a prototype application that aimed to improve IBM employees' experience in reading the news. SuperNews merged heterogeneous news feeds and presented a consistent interface to users. Users could choose to read news on the Web, in e-mail, or as engaging visualizations. Using text processing technology, SuperNews discovered meta-information in articles and created new ways to browse the news collection. SuperNews also allowed users to publish their own columns, as well as annotate and recommend articles to their colleagues. Starting with a range of uncoordinated feeds, SuperNews transformed the solitary reading of news into an engaging and visually appeal ing community experience.

Information extraction: beyond document retrieval

In this paper we give a synoptic view of the growth of the text processing technology of information extraction (IE) whose function is to extract information about a pre‐specified set of entities, relations or events from natural language texts and to record this information in structured representations called templates. Here we describe the nature of the IE task, review the history of the area from its origins in AI work in the 1960s and 70s till the present, discuss the techniques being used to carry out the task, describe application areas where IE systems are or are about to be at work, and conclude with a discussion of the challenges facing the area. What emerges is a picture of an exciting new text processing technology with a host of new applications, both on its own and in conjunction with other technologies, such as information retrieval, machine translation and data mining.

Third party consulting in the network environment (abstract only)

CONFER, first used at Wayne State University in 1979, has proven itself to be an extremely useful and adaptable communications medium. Some examples of present CONFER applicatons at WSU are: Computing Center Staff CONFERence Presently used to coordinate communication between the 180 staff members of the CSC. Communications between various departments isolated by distance and responsibility has been improved. Specialty CONFERences CONFERences exist on such varied topics as school transportation, text processing, nursing education, microcomputers and instructional technology. Project Management Used by the University's PLATO development staff for cross-campus management decision-making and communication. CONFER has reduced the need for staff meetings, has served as a "tracking device" for personnel appointments, and has kept a detailed log of project decisions. CONFER has also been used for CSC project development, notably for the design of an MTS Help Facility. Academic Communications CONFER has been used to facilitate communication between students in an undergraduate Computer Science course, for graduate students in Instructional Technology, and for individual student projects. This summer, a CONFERence will be implemented which will manage course communications for 300 students in a freshman Computer Science course.