• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.4
• /
• pp.510-518
• /
• 2022

The diagnostic evaluation conducted at the national level is very important to detect underachievers in school early. This study used an artificial intelligence method to find the characteristics of underachievers that affect learning development for middle school students. In this study an artificial intelligence model was constructed and analyzed to determine whether the Busan Education Longitudinal Data in 2020 by entering data from the first year of middle school in 2019. A predictive model was developed to predict basic middle school Korean, English, and mathematics education with machine learning algorithms, and it was confirmed that the accuracy was 78%, 82%, and 83%, respectively, in the prediction for the next school year. In addition, by drawing an achievement prediction decision tree for each middle school subject we are analyzing the process of prediction. Finally, we examined what characteristics affect achievement prediction.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.334-342
• /
• 2022

Nowadays, as we can notice on social media, most users choose to use more than one language in their online postings. Thus, social media analytics needs reviewing as code-switching analytics instead of traditional analytics. This paper aims to present evidence comparable to the accuracy of code-switching analytics techniques in analysing the mood state of social media users. We conducted a systematic literature review (SLR) to study the social media analytics that examined the effectiveness of code-switching analytics techniques. One primary question and three sub-questions have been raised for this purpose. The study investigates the computational models used to detect and measures emotional well-being. The study primarily focuses on online postings text, including the extended text analysis, analysing and predicting using past experiences, and classifying the mood upon analysis. We used thirty-two (32) papers for our evidence synthesis and identified four main task classifications that can be used potentially in code-switching analytics. The tasks include determining analytics algorithms, classification techniques, mood classes, and analytics flow. Results showed that CNN-BiLSTM was the machine learning algorithm that affected code-switching analytics accuracy the most with 83.21%. In addition, the analytics accuracy when using the code-mixing emotion corpus could enhance by about 20% compared to when performing with one language. Our meta-analyses showed that code-mixing emotion corpus was effective in improving the mood analytics accuracy level. This SLR result has pointed to two apparent gaps in the research field: i) lack of studies that focus on Malay-English code-mixing analytics and ii) lack of studies investigating various mood classes via the code-mixing approach.

• Journal of the Korea Convergence Society
• /
• v.6 no.6
• /
• pp.263-270
• /
• 2015

L2 learners deal with communication problems encountered during the course of their oral communication by employing what are known as communication strategies(CSs). As CSs play a significant role in communication and language learning, identifying CSs that facilitate communication has become important in L2 research. However, there have been some controversies about how to identify CSs, especially about data sources: conversation data, retrospective interview data, or combining two types of data. Drawing on the advantages of converged data, this study aimed to identify CSs that L2 learners use in their English communication through a convergence analysis of data. In this qualitative case study, the data were collected from Korean L2 learners' conversations and retrospective verbal reports in stimulated recall interviews. Using a data convergence approach, various CSs were identified: definition replacement CSs, message change CSs, time-gaining CSs, and comprehension CSs. This study suggests the effectiveness of CSs in handling L2 communication problems and the usefulness of data convergence in L2 CS research.

• Journal of Family Resource Management and Policy Review
• /
• v.17 no.4
• /
• pp.145-170
• /
• 2013

The purpose of this study was to figure out married female immigrants' experience and process of investing in human capital in Korea. The participants were 11 women from multicultural families who had experience of investing in human capital in Korea, could communicate in the Korean language, and were living in Daegu. The data were collected using intensive interviews. The major findings were as follows: The participants' level of education and work experience in native country were not accepted as human capital and offered no advantages or obtaining employment in Korea, while English language skills were useful for those pursuing an English lecturer position. The motives for investing in human capital were 'adjusting to early stage of marriage and a new environments', 'for their childrens' education', 'to improve female immigrants' level of education', 'seeking a better job', and 'advocating more education'. The types of investing in human capital were 'learning Korean language and culture', 'applying to Open University or taking a middle or high school qualification examination', 'obtaining certification', and 'entering regular university'. The participants' plans for investing in the future were 'finding their own job', 'entering regular university', and 'participating in useful educational programs including Korean language skills for daily life' The results showed that the participants' motives for investing in human capital were related in the stage of their marriage. The phases and changes in their motives during a marriage proved that the participants continued to invest in human capital according to their needs and situation.

• Journal of KIISE
• /
• v.42 no.4
• /
• pp.512-521
• /
• 2015

Internet users purchase goods on the Internet and express their positive or negative emotions of the goods in product reviews. Analysis of the product reviews become critical data to both potential consumers and to the decision making of enterprises. Therefore, the importance of opinion mining techniques which derive opinions by analyzing meaningful data from large numbers of Internet reviews. Existing studies were mostly based on comments written in English, yet analysis in Korean has not actively been done. Unlike English, Korean has characteristics of complex adjectives and suffixes. Existing studies did not consider the characteristics of the Internet language. This study proposes an emotional classification method which increases the accuracy of emotional classification by analyzing the characteristics of the Internet language connoting feelings. We can classify positive and negative comments about products automatically using the Internet emoticon. Also we can check the validity of the proposed algorithm through the result of high precision, recall and coverage for the evaluation of this method.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.5
• /
• pp.267-278
• /
• 2017

As the same letter can be pronounced differently depending on word contexts, one should refer to a lexicon in order to pronounce a word correctly. Phonetic alphabets that lexicons adopt as well as pronunciations that lexicons describe for the same word can be different from lexicon to lexicon. In this paper, we use a sequence-to-sequence model that is widely used in deep learning research area in order to convert automatically from one pronunciation to another. The 12 seq2seq models are implemented based on pronunciation training data collected from 4 different lexicons. The exact accuracy of the models ranges from 74.5% to 89.6%. The aim of this study is the following two things. One is to comprehend a property of phonetic alphabets and pronunciations used in various lexicons. The other is to understand characteristics of seq2seq models by analyzing an error.

• Journal of Korean language education
• /
• v.28 no.4
• /
• pp.337-366
• /
• 2017

This study examines the acquisition of the multiple semantic functions of the Korean adverbial particle -ey by L1 American English learners of Korean as a second language at U.S. institutions. Participants at beginning, intermediate, and advanced proficiency levels (N = 45) were tested on the ability to interpret and produce five of the meanings of -ey, which they had been taught in formal classroom settings in the first semester of their Korean language learning. The results show different developmental trajectories for the particle's different semantic functions. The findings of a statistical analysis indicate that the beginning and intermediate proficiency learners had largely acquired the time, goal, and stative location meanings, but not the contact and unit meanings; the advanced learners demonstrated acquisition of all except for the unit meaning. The study suggests that in addition to factors such as semantic complexity and cross-linguistic influence, several other factors including L2 frequency, the availability of linguistic input, and instructional method also contribute to the acquisition of -ey.

• Journal of the Korea Convergence Society
• /
• v.10 no.11
• /
• pp.55-61
• /
• 2019

In order to realize foreign language education, various existing educational media have been provided, but there are disadvantages in that the cost of the parish and the media program is high and the real-time responsiveness is poor. In this paper, we propose an artificial intelligence English conversation system based on VR and speech recognition. We used Google CardBoard VR and Google Speech API to build the system and developed artificial intelligence algorithms for providing virtual reality environment and talking. In the proposed speech recognition server system, the sentences spoken by the user can be divided into word units and compared with the data words stored in the database to provide the highest probability. Users can communicate with and respond to people in virtual reality. The function provided by the conversation is independent of the contextual conversations and themes, and the conversations with the AI assistant are implemented in real time so that the user system can be checked in real time. It is expected to contribute to the expansion of virtual education contents service related to the Fourth Industrial Revolution through the system combining the virtual reality and the voice recognition function proposed in this paper.

• Journal of English Language & Literature
• /
• v.54 no.4
• /
• pp.483-509
• /
• 2008

For the last decades, criticism on Frankenstein has tried to make a link between Victor's Creature and Rousseaurean "man in a state of nature." Like the Rousseaurean savage in a state of animal, the monster has only basic instincts least needed for his survival, i.e. self-preservation, but turns into a civilized man after learning language. Most critics argue that, despite the monster's acquisition of language, his failure in entry into a cultural and linguistic community is the outcome of a lack of sympathy for him by others, which displays the stark existence of epistemological barriers between them. That is to say, the monster imagines his being the same as others in the pre-linguistic stage but, in the linguistic stage, he realizes that he is different from others. Interpreting the Rousseaurean idea of language, which appears in his writings, as much more focused on emotion than many critics think, I read the dispute between Victor and his Creature as a variation of parent-offspring conflict. Shelley criticizes Rousseau's parental negligence in putting his children into a foundling hospital and leaving them dying there. The monster's revenge on uncaring Victor parallels the likely retaliation Rousseau's displaced children would perform against Rousseau, which Shelley imaginatively reproduces in her novel. The conflict between the monster and Victor is due to a disrupted attachment between parent and child in terms of Darwinian developmental psychology. Affective asynchrony between parent and child, which refers to a state of lack of mutual favorable feelings, accounts for numerous dysfunctional families. This paper shifts a focus from a semiotics-oriented perspective on the monster's social isolation to a Darwinian perspective, drawing attention to emotional problems transpiring in familial interactions. In doing so, it finds that language is a means of communicating one's internal emotions to others along with other means such as facial expressions and body movements. It also demonstrates that how to promote emotional well-being in either familial or social relationships entirely depends on the way in which one employs language that can entail either pleasure or anger on hearers' part.

• Journal of English Language & Literature
• /
• v.54 no.1
• /
• pp.31-60
• /
• 2008

As a way to situate environmental literary study, urban nature recently seems to have become an increasingly important part of ecocritical studies. Considering the recent deprecation on the alleged ecocriticism's ecocentric position, this move looks promising. However, a scrutable review of recent publications of ecocritical studies reveals a contradicting result that an ecocritical approach to urban nature not only lacks substance but also makes too much of the cultural and political issues of 'environmental justice' in which the traditional value and beauty of nature is totally sacrificed and neglected for its political purpose. Under the current circumstance that the environmental crisis threatens all landscapes of wild, rural, and urban, ecocriticism needs to put together "green" landscapes of wildness and "brown" landscapes of urban environment. The interdependence between outback and urban landscapes is best observed in suburban areas in which both landscapes coexist and merge. Provided with due learning and attention of nonhuman environment in their backyard, suburban residents have privilege of both appreciating nature's beauty and value of its own, on the one hand, and acutely reckoning urban environmental concerns related to their health, safety, and sustenance, on the other, in their own home grounds. The post-1980s in the United States has witnessed the emerging voices of suburban nature writings that speak for both green and brown landscapes, which have escaped from ecocritical attention. Among the suburban nature writings, those of Michael Pollan and Thomas Mitchell well illustrate how the green and brown landscapes are interwoven and, accordingly, how environmental awareness of both landscapes can start in suburban 'home.' Ecocriticism's validation as relevant studies of literature and environment may depend on these suburban nature writings which demonstrate an 'ancient-future' ethic of "home" based environmentalism.