• The Journal of the Convergence on Culture Technology
• /
• v.6 no.2
• /
• pp.449-454
• /
• 2020

This paper proposes a machine learning-based emotion analysis system that detects a user's depression through their SNS posts. We first made a list of keywords related to depression in Korean, then used these to create a training data by crawling Twitter data - 1,297 positive and 1,032 negative tweets in total. Lastly, to identify the best machine learning model for text-based depression detection purposes, we compared RNN, LSTM, and GRU in terms of performance. Our experiment results verified that the GRU model had the accuracy of 92.2%, which is 2~4% higher than other models. We expect that the finding of this paper can be used to prevent depression by analyzing the users' SNS posts.

• Journal of Korean Elementary Science Education
• /
• v.22 no.1
• /
• pp.109-120
• /
• 2003

The purpose of this study is to observe, to analyze of the preservice teachers' naive theories about the change of season. And it is to find a instruction strategy which can solve problem about this. The general idea about the change of season is observed by the 3 methods which are simply explaining with words, explaining with pictures and models. The author is to find the similarity. difference and relationship which the preservice teachers have about the general idea about the change of season. The important changable primary factors, which can effect to the general Idea formation, are naturally dragged out through the observation of preservice teachers participation. For this study, 4 first year preservice teachers of one of national university of education are used. Before the interview. the author tries to form rapport with the preservice teachers. Experiment materials, pencil. paper, camcorder, digital recorder and interview note were used for the study with reflection of them just way they are. As the result of the interview. all of 4 preservice teachers had not being understand the concept about the change of season and the three ways of explanation methods were not matched each other, so it is revealed that the general Idea of the change of season, which the preservice teachers have, is not strongly formed. In spite of the repeated study of the change of season from elementary school to university, it has many problem about recognition of the general idea about the change of season which pre-elementary teachers have. Therefore it is needed to improve the experiment in elementary science text book and naive theories by the activity which is explaining the change of season in three dimension space. to prevent the naive theories which the preservice teachers may have.

• Phonetics and Speech Sciences
• /
• v.7 no.3
• /
• pp.139-149
• /
• 2015

This paper aims to analyze pronunciation variations of loanwords produced by Korean and improve the performance of pronunciation modeling of loanwords in Korean by using syllable-based segmentation and phonological knowledge. The loanword text corpus used for our experiment consists of 14.5k words extracted from the frequently used words in set-top box, music, and point-of-interest (POI) domains. At first, pronunciations of loanwords in Korean are obtained by manual transcriptions, which are used as target pronunciations. The target pronunciations are compared with the standard pronunciation using confusion matrices for analysis of pronunciation variation patterns of loanwords. Based on the confusion matrices, three salient pronunciation variations of loanwords are identified such as tensification of fricative [s] and derounding of rounded vowel [ɥi] and [$w{\varepsilon}$]. In addition, a syllable-based segmentation method considering phonological knowledge is proposed for loanword pronunciation modeling. Performance of the baseline and the proposed method is measured using phone error rate (PER)/word error rate (WER) and F-score at various context spans. Experimental results show that the proposed method outperforms the baseline. We also observe that performance degrades when training and test sets come from different domains, which implies that loanword pronunciations are influenced by data domains. It is noteworthy that pronunciation modeling for loanwords is enhanced by reflecting phonological knowledge. The loanword pronunciation modeling in Korean proposed in this paper can be used for automatic speech recognition of application interface such as navigation systems and set-top boxes and for computer-assisted pronunciation training for Korean learners of English.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.29 no.6
• /
• pp.50-61
• /
• 2002

As recognition and polices for plans to preserve natural resources and to develop environment-friendly space in school education is developed, not only organization of curriculums related to these is required but also facilities for the education are indispensable. Therefore, this study tries to suggest several standards on matters including kinds and scale of facilities and the introduction of species by facilities required for outdoor teaming spaces for environmental education in the elementary school system. The methods of this study include researching various records related to environmental education in elementary school, researching the present condition of outdoor learning space installed and operating in the existing schools by making an on-the-spot survey, and analyzing appearance frequencies of plants and animals displayed in the text. In addition, the actual conditions of the facility use and management were investigate through a questionnaire, We chose and diagrammed a model of the installed facilities by putting the results together. For analyses the investigated eight schools, were categorized as ‘facilities-arranged type’or ‘connection type with ecological park’. The first type distributed and arranged facilities, including meteorological observatory, rocky park, experience-learning area, ecological pond, animal-breeding farm and field-leaning area into appropriate locations according to the site conditions of the school while the second type created a natural learning place by integrating several facilities and arranging areas such as an animal-breeding farm and experience-learning area into appropriate sites. In this study, essential facilities for outdoor learning are classified into ecological park, experience-loaming area, field loaming area, and for natural learning, meteorological observatory, animal-breeding farm, and greenhouse.

• The KIPS Transactions:PartB
• /
• v.10B no.7
• /
• pp.829-836
• /
• 2003

In this paper, we propose a stochastic model for sentence speech understanding using dictionary and thesaurus. The proposed model extracts words from an input speech or text into a sentence. A computer is sellected category of dictionary database compared the word extracting from the input sentence calculating a probability value to the compare results from stochastic model. At this time, computer read out upper dictionary information from the upper dictionary searching and extracting word compared input sentence caluclating value to the compare results from stochastic model. We compare adding the first and second probability value from the dictionary searching and the upper dictionary searching with threshold probability that we measure the sentence understanding rate. We evaluated the performance of the sentence speech understanding system by applying twenty questions game. As the experiment results, we got sentence speech understanding accuracy of 79.8%. In this case, probability ($\alpha$) of high level word is 0.9 and threshold probability ($\beta$) is 0.38.

• Cross-Cultural Studies
• /
• v.26
• /
• pp.405-444
• /
• 2012

This paper is based on the view that film should be conceived as a form of cultural practice whose meaning is always in the process of being produced within diverse socio-cultural contexts and aims to examine the ways in which the meaning of Korean film is (re)mediated or received in diverse cultural contexts outside the country. In this paper, we employ two theoretical grounds. Firstly, it positions itself in line with the audience studies within the field of cultural studies where the audience is conceived as active agents who produce the meaning of a popular culture text. The recruitment of the theoretical propositions from the audience studies enables recognition of the significance of the reception in film practice which recently seems to be oriented on production and distribution. Secondly, we conceive transnationality of film as that which is being produced in the process of transaction between the film and the audience, that is to say, transnationality is a form of discourse that emerges upon cultural interaction. The empirical work involves examination of a set of reviews of four films--Chihwaseon, Oldboy, Thirt, Poety--that have been published in daily newspapers and some popular film magazines in the U. S., the U. K. and France. Through the analysis of the film reviews, we identify four interpretive schemes or rather discourses recruited via which the Korean films are approached and understood: auteurism, formalism, universal themes, emotional response. We propose that these four kinds of discourse provide a common ground for the audience from different cultural backgrounds to understand Korean film. Furthermore, we also suggest that transnationality of Korean cinema needs to be reconsidered in terms of the reception as the audience from different socio-cultural backgrounds should be understood as active agents who are capable of engaging in Korean cultural texts such as film in their own way producing various meanings and these are also constituent of the meaning of the cultural texts.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.466-472
• /
• 2021

Speaker Change Detection (SCD) refers to finding the moment when the main speaker changes from one person to the next in a speech conversation. In speaker change detection, difficulties arise due to overlapping speakers, inaccuracy in the information labeling, and data imbalance. To solve these problems, TIMIT corpus widely used in speech recognition have been concatenated artificially to obtain a sufficient amount of training data, and the detection of changing speaker has performed after identifying overlapping speakers. In this paper, we propose an speaker change detection system that considers the speaker overlapping. We evaluated and verified the performance using various approaches. As a result, a detection system similar to the X-Vector structure was proposed to remove the speaker overlapping region, while the Bi-LSTM method was selected to model the speaker change system. The experimental results show a relative performance improvement of 4.6 % and 13.8 % respectively, compared to the baseline system. Additionally, we determined that a robust speaker change detection system can be built by conducting related studies based on the experimental results, taking into consideration text and speaker information.

• Knowledge Management Research
• /
• v.20 no.2
• /
• pp.25-42
• /
• 2019

AI speakers which are wireless speakers with smart features have released from many manufacturers and adopted by many customers. Though smart features including voice recognition, controlling connected devices and providing information are embedded in many mobile phones, AI speakers are sitting in home and has a role of the central en-tertainment and information provider. Many surveys have investigated the important factors to adopt AI speakers and influ-encing factors on satisfaction. Though most surveys on AI speakers are cross sectional, we can track customer attitude toward AI speakers longitudinally by analyzing customer reviews on AI speakers. However, there is not much research on the change of customer attitude toward AI speaker. Therefore, in this study, we try to grasp how the attitude of AI speaker changes with time by applying text mining-based analysis. We collected the customer reviews on Amazon Echo which has the highest share of AI speakers in the global market from Amazon.com. Since Amazon Echo already have two generations, we can analyze the characteristics of reviews and compare the attitude ac-cording to the adoption time. We identified all sub topics of customer reviews and specified the topics for smart features. And we analyzed how the share of topics varied with time and analyzed diverse meta data for comparisons. The proportions of the topics for general satisfaction and satisfaction on music were increasing while the proportions of the topics for music quality, speakers and wireless speakers were decreasing over time. Though the proportions of topics for smart fea-tures were similar according to time, the share of the topics in positive reviews and importance metrics were reduced in the 2nd generation of Amazon Echo. Even though smart features were mentioned similarly in the reviews, the influential effect on satisfac-tion were reduced over time and especially in the 2nd generation of Amazon Echo.

• The Journal of the Korea Contents Association
• /
• v.19 no.8
• /
• pp.44-57
• /
• 2019

As dance performances in the theater space are centered on text, they have plots and make characters stand out. They also emphasize expressivity and technique, and their recognition of space is very modern and typical of dichotomous Cartesian thinking. The museum space has many similarities with the theater space in that it is a result of modernity and granted authority to present arts. The performances in museums place value more on the presence than on the representation. For this reason, works in museums, which are frequently presented in recent years, are mainly works of site-specific or performative concepts. Now, rather than being able to obtain from aesthetics defined as works, the museum is assured its own aesthetic production and justification, paying attention to the performance as an event occurring now and here.

• 한국체육학회지인문사회과학편
• /
• v.56 no.1
• /
• pp.99-110
• /
• 2017

The purpose of this study was to focus on the social influence of the movie , to review the meaning and symbolism of Koreans living in Japan (ざいにち) and rugby in the movie, and to eventually reveal the messages from the movie. The research method was text analysis. As a result, Koreans living in Japan were represented in 2 ways. Koreans living in Japan were represented as Homo Sacer, the contradictory being, located inside society by Japan's sovereignty but considered as outsiders. Meanwhile, the identity of Koreans living in Japan were represented clearly as Korean and they were acknowledged in Japan as proud and capable. The rugby in the movie has 2 symbolic meanings. First, it was the most important and effective way to prove Korean existence in Japan by representing the struggle for recognition, additionally it also carried an important message about their ideal society.