• Journal of Industrial Convergence
• /
• v.22 no.4
• /
• pp.11-19
• /
• 2024

The purpose of this study was to analyze user reviews of running applications using text mining. This study used user reviews of Nike Run Club and Runkeeper in the Google Play Store using the selenium package of python3 as the analysis data, and separated the morphemes by leaving only Korean nouns through the OKT analyzer. After morpheme separation, we created a rankNL dictionary to remove stopwords. To analyze the data, we used TF, TF-IDF and LDA topic modeling in text mining. The results of this study are as follows. First, the keywords 'record', 'app', and 'workout' were identified as the top keywords in the user reviews of Nike Run Club and Runkeeper applications, and there were differences in the rankings of TF and TF-IDF. Second, the LDA topic modeling of Nike Run Club identified the topics of 'basic items', 'additional features', 'errors', and 'location-based data', and the topics of Runkeeper identified the topics of 'errors', 'voice function', 'running data', 'benefits', and 'motivation'. Based on the results, it is recommended that errors and improvements should be made to contribute to the competitiveness of the application.

• Phonetics and Speech Sciences
• /
• v.16 no.1
• /
• pp.67-76
• /
• 2024

Recent advances in text-to-speech (TTS) technology have significantly improved the quality of synthesized speech, reaching a level where it can closely imitate natural human speech. Especially, TTS models offering various voice characteristics and personalized speech, are widely utilized in fields such as artificial intelligence (AI) tutors, advertising, and video dubbing. Accordingly, in this paper, we propose a one-shot multi-speaker TTS system that can ensure acoustic diversity and synthesize personalized voice by generating speech using unseen target speakers' utterances. The proposed model integrates a speaker encoder into a TTS model consisting of the FastSpeech2 acoustic model and the HiFi-GAN vocoder. The speaker encoder, based on the pre-trained RawNet3, extracts speaker-specific voice features. Furthermore, the proposed approach not only includes an English one-shot multi-speaker TTS but also introduces a Korean one-shot multi-speaker TTS. We evaluate naturalness and speaker similarity of the generated speech using objective and subjective metrics. In the subjective evaluation, the proposed Korean one-shot multi-speaker TTS obtained naturalness mean opinion score (NMOS) of 3.36 and similarity MOS (SMOS) of 3.16. The objective evaluation of the proposed English and Korean one-shot multi-speaker TTS showed a prediction MOS (P-MOS) of 2.54 and 3.74, respectively. These results indicate that the performance of our proposed model is improved over the baseline models in terms of both naturalness and speaker similarity.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.539-549
• /
• 2024

This study employed text mining techniques like frequency analysis, word clouds, and LDA topic modeling to assess consumer satisfaction and dissatisfaction with Hyundai Motor Company in the Chinese market, compared to brands such as Toyota, Volkswagen, Buick, and Geely. Focusing on compact vehicles from these brands between 2021 and 2023, this study analyzed customer reviews. The results indicated Hyundai Avante's positive factors, including a long wheelbase. However, it also highlighted dissatisfaction aspects like Manipulate, engine performance, trunk space, chassis and suspension, safety features, quantity and brand of audio speakers, music membership service, separation band, screen reflection, CarLife, and map services. Addressing these issues could significantly enhance Hyundai's competitiveness in the Chinese market. Previous studies mainly focused on literature research and surveys, which only revealed consumer perceptions limited to the variables set by the researchers. This study, through text mining and comparing various car brands, aims to gain a deeper understanding of market trends and consumer preferences, providing useful information for marketing strategies of Hyundai and other brands in the Chinese market.

• Journal of The Korean Association For Science Education
• /
• v.6 no.2
• /
• pp.1-7
• /
• 1986

The summary of the distinguishing features of the program(developed In this research) 1. For the high school physics 1, total of 67 kinds of physical concepts. 31 of physical low. 84 of equations. 23 of units, and 191 of new sample problems were imputed (in the data file) 2. Physical concepts, lows, equations, and units could be studied by chapter 3. Among 191 of sample problems, the user can choose his own set of problems according to chapters and difficulties. 4. The content, a set of problems chosen, and a result for test will be printed for a hard copy. 5. An extra effect was done to use same character for physical quantities as in a text book.

• Journal of Computing Science and Engineering
• /
• v.6 no.2
• /
• pp.143-150
• /
• 2012

Computational techniques for topic classification can support qualitative research by automatically applying labels in preparation for qualitative analyses. This paper presents an evaluation of supervised learning techniques applied to one such use case, namely, that of labeling emotions, instructions and information in suicide notes. We train a collection of one-versus-all binary support vector machine classifiers, using cost-sensitive learning to deal with class imbalance. The features investigated range from a simple bag-of-words and n-grams over stems, to information drawn from syntactic dependency analysis and WordNet synonym sets. The experimental results are complemented by an analysis of systematic errors in both the output of our system and the gold-standard annotations.

• English Language & Literature Teaching
• /
• v.11 no.4
• /
• pp.209-235
• /
• 2005

The purpose of the present study was to investigate the effectiveness of reciprocal teaching procedure for improving Korean college students' reading comprehension of English text. In particular, this study sought to explore the qualitative features, if any, in students' use of reading comprehension strategies presented in the process of Reciprocal Reading Procedure (RRP). In order to accomplish the goal of the study, transcripts of the students' dialogues, open-ended questionnaires, and researchers' observation notes were examined. The results of the study showed that the participants used different four kinds of reading strategies in the process of RRP (questioning, clarifying, predicting, summarizing). The findings also suggested that the readers with limited knowledge of vocabulary had difficulty in moving on to the next level. Additionally, future research direction and some pedagogical implications are presented for the practical EFL classroom.

• ETRI Journal
• /
• v.40 no.2
• /
• pp.257-265
• /
• 2018

Pronouns are frequently dropped in Korean sentences, especially in text messages in the mobile phone environment. Restoring dropped pronouns can be a beneficial preprocessing task for machine translation, information extraction, spoken dialog systems, and many other applications. In this work, we address the problem of dropped pronoun recovery by resolving two simultaneous subtasks: detecting zero-pronoun sentences and determining the type of dropped pronouns. The problems are statistically modeled by encoding the sentence and classifying types of dropped pronouns using a recurrent neural network (RNN) architecture. Various RNN-based encoding architectures were investigated, and the stacked RNN was shown to be the best model for Korean zero-pronoun recovery. The proposed method does not require any manual features to be implemented; nevertheless, it shows good performance.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.7
• /
• pp.76-90
• /
• 1994

In this paper, an efficient algorithm is proposed which recognizes the mixed document consisting of the printed Korean/alphanumeric texts and graphic images. In the preprocessing step an input document is aligned if necessary by rotating it. We obtain the rotation angle using the Hough transform and align the input document horizontally. Then we separate graphic image parts from text parts by considering chain codes of connected components. We further separate each character using vertical and horizontal projections. In the recognition step Korean and alphanumeric characters are classified and each of them is recognized hierarchically using several features. In summary an efficient recognition algorithm for mixed documents is proposed and its performance is demonstrated via computer simulations.

• International Journal of Knowledge Content Development & Technology
• /
• v.5 no.2
• /
• pp.75-101
• /
• 2015

In this paper, we investigate the notion of error correction memory applied to technical texts. The main purpose is to introduce flexibility and context sensitivity in the detection and the correction of errors related to Constrained Natural Language (CNL) principles. This is realized by enhancing error detection paired with relatively generic correction patterns and contextual correction recommendations. Patterns are induced from previous corrections made by technical writers for a given type of text. The impact of such an error correction memory is also investigated from the point of view of the technical writer's cognitive activity. The notion of error correction memory is developed within the framework of the LELIE project an experiment is carried out on the case of fuzzy lexical items and negation, which are both major problems in technical writing. Language processing and knowledge representation aspects are developed together with evaluation directions.

• Annual Conference on Human and Language Technology
• /
• 1997.10a
• /
• pp.7-14
• /
• 1997

문서 범주화에서 문서의 내용에 따라 적합한 범주의 종류와 수를 찾는 문제를 해결하기 위해서는 문서 당 하나의 범주를 할당할 경우에 가장 좋은 성능을 보이는 모델이 효과적일 것이다. 그러므로, 본 논문에서는 문서 당 하나의 범주를 할당할 경우에 좋은 결과를 보이는 k-nearest neighbor 방법을 이용한다. 그리고 k-nearest neighbor 방법을 이용한 문서 범주화의 성능을 향상시키기 위해서, 문서 표현에 사용하는 단어들을 범주 자질의 성격을 갖는 단어들로 제한하는 방법을 제안한다. 제안한 방법은 Router 신문 일년치로 구성된 Router-21578 테스트 집합에서 breakeven point 82%라는 좋은 결과를 보였다.