• Journal of the Ergonomics Society of Korea
• /
• v.31 no.2
• /
• pp.291-298
• /
• 2012

Objective: The aim of this study is to predict Korean text entry on touchscreens using ACT-R cognitive architecture. Background: Touchscreen application in devices such as satellite navigation devices, PDAs, mobile phones, etc. has been increasing, and the market size is expanding. Accordingly, there is an increasing interest to develop and evaluate the interface to enhance the user experience and increase satisfaction in the touchscreen environment. Method: In this study, Korean text entry performance in the touchscreen environment was analyzed using ACT-R. The ACT-R model considering the characteristics of the Korean language which is composed of vowels and consonants was established. Further, this study analyzed if the prediction of Korean text entry is possible through the ACT-R cognitive model. Results: In the analysis results, no significant difference on performance time between model prediction and empirical data was found. Conclusion: The proposed model can predict the accurate physical movement time as well as cognitive processing time. Application: This study is useful in conducting model-based evaluation on the text entry interface of the touchscreen and enabled quantitative and effective evaluation on the diverse types of Korean text input interfaces through the cognitive models.

• Journal of Korea Society of Industrial Information Systems
• /
• v.22 no.2
• /
• pp.43-52
• /
• 2017

Pattern Analysis is One of the Most Important Techniques in the Signal and Image Processing and Text Mining Fields. Discrete Fourier Transform (DFT) is Generally Used to Analyzing the Pattern of Signals and Images. We thought DFT could also be used on the Analysis of Text Patterns. In this Paper, DFT is Firstly Adapted in the World to the Sentence Plagiarism Detection Which Detects if Text Patterns of a Document Exist in Other Documents. We Signalize the Texts Converting Texts to ASCII Codes and Apply the Cross-Correlation Method to Detect the Simple Text Plagiarisms such as Cut-and-paste, term Relocations and etc. WordNet is using to find Similarities to Detect the Plagiarism that uses Synonyms, Translations, Summarizations and etc. The Data set, 2013 Corpus, Provided by PAN Which is the One of Well-known Workshops for Text Plagiarism is used in our Experiments. Our Method are Fourth Ranked Among the Eleven most Outstanding Plagiarism Detection Methods.

• Journal of KIISE:Software and Applications
• /
• v.35 no.5
• /
• pp.325-334
• /
• 2008

The goal of text categorization is to classify documents into a certain number of pre-defined categories. The previous studies in this area have used a large number of labeled training documents for supervised learning. One problem is that it is difficult to create the labeled training documents. While it is easy to collect the unlabeled documents, it is not so easy to manually categorize them for creating training documents. In this paper, we propose a new text categorization method based on semi-supervised learning. The proposed method uses only unlabeled documents and keywords of each category, and it automatically constructs training data from them. Then a text classifier learns with them and classifies text documents. The proposed method shows a similar degree of performance, compared with the traditional supervised teaming methods. Therefore, this method can be used in the areas where low-cost text categorization is needed. It can also be used for creating labeled training documents.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.8
• /
• pp.251-258
• /
• 2020

A training dataset for text summarization consists of pairs of a document and its summary. As conventional approaches to building text summarization dataset are human labor intensive, it is not easy to construct large datasets for text summarization. A collection of news articles is one of the most popular resources for text summarization because it is easily accessible, large-scale and high-quality text. From social media news services, we can collect not only headlines and subheads of news articles but also summary descriptions that human editors write about the news articles. Approximately 425,000 pairs of news articles and their summaries are collected from social media. We implemented an automatic extractive summarizer and trained it on the dataset. The performance of the summarizer is compared with unsupervised models. The summarizer achieved better results than unsupervised models in terms of ROUGE score.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.5
• /
• pp.467-474
• /
• 2018

To organize and document the contents of meetings and discussions is very important in various tasks. However, in the past, people had to manually organize the contents themselves. In this paper, we describe the development of a system that generates the meeting minutes automatically using the TextRank algorithm. The proposed system records all the utterances of the speaker in real time and calculates the similarity based on the appearance frequency of the sentences. Then, to create the meeting minutes, it extracts important words or phrases through a non-supervised learning algorithm for finding the relation between the sentences in the document data. Especially, we improved the performance by introducing the keyword weighting technique for the TextRank algorithm which reconfigured the PageRank algorithm to fit words and sentences.

• The Journal of the Korea Contents Association
• /
• v.12 no.5
• /
• pp.52-61
• /
• 2012

Text visualization is one of sectors in data visualization. This study is on methods to visually represent text's contents, structure, and form aspects based on various analytic techniques about wide range of text data. In this study -as a text visualization study-, 1) a method to find out the characteristics of a book's genre using words in the text of the book was looked into, 2) elements of visualization of a book's genre based on verification through an experiment were drew, and 3) the ways to intuitionally and efficiently visualize this were explained. According to visualization suggested by this study, first, actual genre of a book can be understood based on words used in the book. Second, with which genre is closed to the book can be found out with one glance through images of visualization. Moreover, the characteristics of complicated genres included in a book can be understood. Furthermore, the level of closeness (similarity) of a genre -which is found to be a representative genre using the number of dots, curvature of a curve, and brightness in the image- can be assumed. Finally, the outcome of this study can be used for a variety of fields including book customizing service such as a book recommendation system that provides images of personal preference books or genres through application of books favored by individual customers.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.13-31
• /
• 2016

Despite expectations of short- or long-term positive effects of corporate social responsibility (CSR) on firm performance, the results of existing research into this relationship are inconsistent partly due to lack of clarity about subordinate CSR concepts. In this study, keywords related to CSR concepts are extracted from atypical sources, such as newspapers, using text mining techniques to examine the relationship between CSR and firm performance. The analysis is based on data from the New York Times, a major news publication, and Google Scholar. We used text analytics to process unstructured data collected from open online documents to explore the effects of CSR on short- and long-term firm performance. The results suggest that the CSR index computed using the proposed text - online media - analytics predicts long-term performance very well compared to short-term performance in the absence of any internal firm reports or CSR institute reports. Our study demonstrates the text analytics are useful for evaluating CSR performance with respect to convenience and cost effectiveness.

• Journal of the Korean Society for information Management
• /
• v.40 no.4
• /
• pp.1-31
• /
• 2023

This study conducted user experience evaluation by introducing various text mining techniques along with topic modeling techniques for mobile menstrual cycle measurement applications that are closely related to women's health and analyzed the results by combining them with a honeycomb model. To evaluate the user experience revealed in the menstrual cycle measurement application review, 47,117 Korean reviews of the menstrual cycle measurement application were collected. Topic modeling analysis was conducted to confirm the overall discourse on the user experience revealed in the review, and text network analysis was conducted to confirm the specific experience of each topic. In addition, sentimental analysis was conducted to understand the emotional experience of users. Based on this, the development strategy of the menstrual cycle measurement application was presented in terms of accuracy, design, monitoring, data management, and user management. As a result of the study, it was confirmed that the accuracy and monitoring function of the menstrual cycle measurement of the application should be improved, and it was observed that various design attempts were required. In addition, the necessity of supplementing personal information and the user's biometric data management method was also confirmed. By exploring the user experience (UX) of the menstrual cycle measurement application in-depth, this study revealed various factors experienced by users and suggested practical improvements to provide a better experience. It is also significant in that it presents a methodology by combines topic modeling and text network analysis techniques so that researchers can closely grasp vast amounts of review data in the process of evaluating user experiences.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.52 no.3
• /
• pp.89-102
• /
• 2024

This study aims to examine the characteristics of the user experience of New Town neighborhood parks and explore issues that diversify the experience of the parks. In order to quantitatively analyze a large amount of park visitors' experiences, text-based Naver blog reviews were collected and analyzed. Among the Phase 1 and 2 New Towns, the parks with the highest user experience postings were selected for each city as the target of analysis. Blog text data was collected from May 20, 2003, to May 31, 2022, and analysis was conducted targeting Ilsan Lake Park, Bundang Yuldong Park, Gwanggyo Lake Park, and Dongtan Lake Park. The findings revealed that all four parks were used for everyday relaxation and recreation. Second, the analysis underscores park's diverse user groups. Third, the programs for parks nearby were also related to park usage. Fourth, the words within the top 20 rankings represented distinctive park elements or content/programs specific to each park. Lastly, the results of the network analysis delineated four overarching types of park users and the networks of four park user types appeared differently depending on the park. This study provides two implications. First, in addition to the naturalistic characteristics, the differentiation of each park's unique facilities and programs greatly improves public awareness and enriches the individual park experience. Second, if analysis of the context surrounding the park based on spatial information is performed in addition to text analysis, the accuracy of interpretation of text data analysis results could be improved. The results of this study can be used in the planning and designing of parks and greenspaces in the Phase 3 New Towns currently in progress.

• ETRI Journal
• /
• v.39 no.4
• /
• pp.455-466
• /
• 2017

This study focuses on a method for sequential data augmentation in order to alleviate data sparseness problems. Specifically, we present corpus expansion techniques for enhancing the coverage of a language model. Recent recurrent neural network studies show that a seq2seq model can be applied for addressing language generation issues; it has the ability to generate new sentences from given input sentences. We present a method of corpus expansion using a sentence-chain based seq2seq model. For training the seq2seq model, sentence chains are used as triples. The first two sentences in a triple are used for the encoder of the seq2seq model, while the last sentence becomes a target sequence for the decoder. Using only internal resources, evaluation results show an improvement of approximately 7.6% relative perplexity over a baseline language model of Korean text. Additionally, from a comparison with a previous study, the sentence chain approach reduces the size of the training data by 38.4% while generating 1.4-times the number of n-grams with superior performance for English text.