• Journal of the Korea Convergence Society
• /
• v.10 no.3
• /
• pp.167-176
• /
• 2019

The conversational agent, which is at the forefront of the 4th industry, aims to personalize the user-centered focus in the future and holds an important position to have a hub that can be connected to various IoT devices. It is a challenge for interactive agents to recognize the user's emotions and provide the correct interaction to personalization. The study first I looked at emotional definitions and scientific and engineering approaches. Then I recognized through social perspectives what social function and what factors emotions have and how they can be used to understand emotions. Based on this, I explored how users can be discovered emotional social factors in communication. This research has shown that social factors can be found in the user's speech, which can be linked to the social meaning of emotions. Finally, I propose a model to discover social factors in user communication. I hope that this will help designer and researcher to study user-centered design and interaction in designing interactive agents.

• Journal of The Korean Association For Science Education
• /
• v.38 no.2
• /
• pp.219-234
• /
• 2018

In this study, we explored the possibility of automating the process of analyzing elements of scientific argument in the context of a Korean classroom. To gather training data, we collected 990 sentences from science education journals that illustrate the results of coding elements of argumentation according to Toulmin's argumentation structure framework. We extracted 483 sentences as a test data set from the transcription of students' discourse in scientific argumentation activities. The words and morphemes of each argument were analyzed using the Python 'KoNLPy' package and the 'Kkma' module for Korean Natural Language Processing. After constructing the 'argument-morpheme:class' matrix for 1,473 sentences, five machine learning techniques were applied to generate predictive models relating each sentences to the element of argument with which it corresponded. The accuracy of the predictive models was investigated by comparing them with the results of pre-coding by researchers and confirming the degree of agreement. The predictive model generated by the k-nearest neighbor algorithm (KNN) demonstrated the highest degree of agreement [54.04% (${\kappa}=0.22$)] when machine learning was performed with the consideration of morpheme of each sentence. The predictive model generated by the KNN exhibited higher agreement [55.07% (${\kappa}=0.24$)] when the coding results of the previous sentence were added to the prediction process. In addition, the results indicated importance of considering context of discourse by reflecting the codes of previous sentences to the analysis. The results have significance in that, it showed the possibility of automating the analysis of students' argumentation activities in Korean language by applying machine learning.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.9
• /
• pp.75-84
• /
• 2012

HMM-based Text-to-Speech systems generally utilize context dependent tri-phone units from a large corpus speech DB to enhance the synthetic speech. To downsize a large corpus speech DB, acoustically similar tri-phone units are clustered based on the decision tree using context dependent information. Context dependent information includes phoneme sequence as well as prosodic information because the naturalness of synthetic speech highly depends on the prosody such as pause, intonation pattern, and segmental duration. However, if the prosodic information was complicated, many context dependent phonemes would have no examples in the training data, and clustering would provide a smoothed feature which will generate unnatural synthetic speech. In this paper, instead of complicate prosodic information we propose a simple three prosodic boundary types and decision tree questions that use rising tone, falling tone, and monotonic tone to improve naturalness. Experimental results show that our proposed method can improve naturalness of a HMM-based Korean TTS and get high MOS in the perception test.

• The Journal of the Korea Contents Association
• /
• v.22 no.2
• /
• pp.10-21
• /
• 2022

In order to improve formal presentation attitudes such as presentation of job interviews and presentation of project results at the company, there are few automated methods other than observation by colleagues or professors. In previous studies, it was reported that the speaker's stable speech and gaze processing affect the delivery power in the presentation. Also, there are studies that show that proper feedback on one's presentation has the effect of increasing the presenter's ability to present. In this paper, considering the positive aspects of correction, we developed a program that intelligently corrects the wrong presentation habits and attitudes of college students through facial analysis of videos and analyzed the proposed program's performance. The proposed program was developed through web-based verification of the use of redundant words and facial recognition and textualization of the presentation contents. To this end, an artificial intelligence model for classification was developed, and after extracting the video object, facial feature points were recognized based on the coordinates. Then, using 4000 facial data, the performance of the algorithm in this paper was compared and analyzed with the case of facial recognition using a Teachable Machine. Use the program to help presenters by correcting their presentation attitude.

• Journal of Korean Elementary Science Education
• /
• v.41 no.1
• /
• pp.30-43
• /
• 2022

In this study, elementary students' science communication competence was investigated based on the grammatical features expressed in their language-use in classroom discourse and science writings. The classes were designed to integrate the evidence-based reasoning framework and traditional learning cycle and were conducted on fifth graders in an elementary school. Eight elementary students' discourse data and writings were analyzed using lexico-grammatical resource analysis, which examined the discourse text's content and logical relations. The results revealed that the student language used in analyzing data, interpreting evidence, or constructing explanations did not precisely conform to the grammatical features in science language use. However, they provided examples of grammatical metaphors by nominalizing observed events in the classroom discourses and those of causal relations in their writings. Thus, elementary students can use science language grammatically from science language-use experiences through listening to a teacher's instructional discourses or recognizing the grammatical structures of science texts in workbooks. The opportunities in which elementary students experience the language-use model in science learning need to be offered to understand the appropriate language use in the epistemic context of evidence-based reasoning and learn literacy skills in science.

• Journal of Practical Engineering Education
• /
• v.15 no.2
• /
• pp.381-388
• /
• 2023

Through artificial neural network education using spreadsheets, non-major undergraduate students can understand the operation principle of artificial neural networks and develop their own artificial neural network software. Here, training of the operation principle of artificial neural networks starts with the generation of training data and the assignment of correct answer labels. Then, the output value calculated from the firing and activation function of the artificial neuron, the parameters of the input layer, hidden layer, and output layer is learned. Finally, learning the process of calculating the error between the correct label of each initially defined training data and the output value calculated by the artificial neural network, and learning the process of calculating the parameters of the input layer, hidden layer, and output layer that minimize the total sum of squared errors. Training on the operation principles of artificial neural networks using a spreadsheet was conducted for undergraduate non-major students. And image training data and basic artificial neural network development results were collected. In this paper, we analyzed the results of collecting two types of training data and the corresponding artificial neural network SW with small 12-pixel images, and presented methods and execution results of using the collected training data for Orange machine learning model learning and analysis tools.

• Journal of The Korean Association For Science Education
• /
• v.41 no.4
• /
• pp.339-358
• /
• 2021

This study explores the agency of a student leader, expressed through efforts to distribute power and encourage participation in elementary scientific modeling classes. The study also analyzes the context in which the leader's agency was expressed and the context in which the development of a collective agency was constrained. The participants were 22 fifth-grade students. The leader's agency was analyzed by examining his words and actions. As a result, at the outset of the study, the leader had the most power, performing all the activities as the sole authority in a non-cooperative participation pattern. However, with reflection and help from the researcher, the leader recognized the problem and facilitated the participation of other students. He developed an identity as a teacher and demonstrated the agency. The leader's agentic behaviors can be categorized into three aspects. First, regarding the cognitive aspect, the leader helped other students participate in modeling by sharing his knowledge. Second, regarding the normative aspect, he made rules to give all students an equal voice. Third, regarding the emotional aspect, the leader acknowledged the contribution of the students, increasing their confidence. The leader's agency temporarily helped the group to overcome the student hierarchy, facilitating a cooperative participation pattern. However, the development of a collective agency was constrained. The power of the leader was partially redistributed, and the other students did not position themselves as equal to the leader. To support the leader's agency to develop into a collective agency, it is necessary to redistribute the power of the leader more equally and to change the recognition of students.