• Journal of the Korea Society of Computer and Information
• /
• v.26 no.12
• /
• pp.53-59
• /
• 2021

In this paper, we propose a BERGPT-chatbot, a domestic AI chatbot that can alleviate negative emotions based on text input such as 'Replika'. We made BERGPT-chatbot into a chatbot capable of mitigating negative emotions by pipelined two models, KR-BERT and KoGPT2-chatbot. We applied a creative method of giving emotions to unrefined everyday datasets through KR-BERT, and learning additional datasets through KoGPT2-chatbot. The development background of BERGPT-chatbot is as follows. Currently, the number of people with depression is increasing all over the world. This phenomenon is emerging as a more serious problem due to COVID-19, which causes people to increase long-term indoor living or limit interpersonal relationships. Overseas artificial intelligence chatbots aimed at relieving negative emotions or taking care of mental health care, have increased in use due to the pandemic. In Korea, Psychological diagnosis chatbots similar to those of overseas cases are being operated. However, as the domestic chatbot is a system that outputs a button-based answer rather than a text input-based answer, when compared to overseas chatbots, domestic chatbots remain at a low level of diagnosing human psychology. Therefore, we proposed a chatbot that helps mitigating negative emotions through BERGPT-chatbot. Finally, we compared BERGPT-chatbot and KoGPT2-chatbot through 'Perplexity', an internal evaluation metric for evaluating language models, and showed the superity of BERGPT-chatbot.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.3
• /
• pp.1-12
• /
• 2024

In this paper, we fine-tuned KoAlpaca, a large-scale Korean language model, and implemented a blog text generation system utilizing it. Blogs on social media platforms are widely used as a marketing tool for businesses. We constructed training data of positive reviews through emotion analysis and refinement of collected sponsored blog texts and applied QLoRA for the lightweight training of KoAlpaca. QLoRA is a fine-tuning approach that significantly reduces the memory usage required for training, with experiments in an environment with a parameter size of 12.8B showing up to a 58.8% decrease in memory usage compared to LoRA. To evaluate the generative performance of the fine-tuned model, texts generated from 100 inputs not included in the training data produced on average more than twice the number of words compared to the pre-trained model, with texts of positive sentiment also appearing more than twice as often. In a survey conducted for qualitative evaluation of generative performance, responses indicated that the fine-tuned model's generated outputs were more relevant to the given topics on average 77.5% of the time. This demonstrates that the positive review generation language model for sponsored content in this paper can enhance the efficiency of time management for content creation and ensure consistent marketing effects. However, to reduce the generation of content that deviates from the category of positive reviews due to elements of the pre-trained model, we plan to proceed with fine-tuning using the augmentation of training data.

• Journal of Intelligence and Information Systems
• /
• v.19 no.3
• /
• pp.113-125
• /
• 2013

Every company wants to know customer's requirement and makes an effort to meet them. Cause that, communication between customer and company became core competition of business and that important is increasing continuously. There are several strategies to find customer's needs, but VOC (Voice of customer) is one of most powerful communication tools and VOC gathering by several channels as telephone, post, e-mail, website and so on is so meaningful. So, almost company is gathering VOC and operating VOC system. VOC is important not only to business organization but also public organization such as government, education institute, and medical center that should drive up public service quality and customer satisfaction. Accordingly, they make a VOC gathering and analyzing System and then use for making a new product and service, and upgrade. In recent years, innovations in internet and ICT have made diverse channels such as SNS, mobile, website and call-center to collect VOC data. Although a lot of VOC data is collected through diverse channel, the proper utilization is still difficult. It is because the VOC data is made of very emotional contents by voice or text of informal style and the volume of the VOC data are so big. These unstructured big data make a difficult to store and analyze for use by human. So that, the organization need to automatic collecting, storing, classifying and analyzing system for unstructured big VOC data. This study propose an intelligent VOC analyzing system based on opinion mining to classify the unstructured VOC data automatically and determine the polarity as well as the type of VOC. And then, the basis of the VOC opinion analyzing system, called domain-oriented sentiment dictionary is created and corresponding stages are presented in detail. The experiment is conducted with 4,300 VOC data collected from a medical website to measure the effectiveness of the proposed system and utilized them to develop the sensitive data dictionary by determining the special sentiment vocabulary and their polarity value in a medical domain. Through the experiment, it comes out that positive terms such as "칭찬, 친절함, 감사, 무사히, 잘해, 감동, 미소" have high positive opinion value, and negative terms such as "퉁명, 뭡니까, 말하더군요, 무시하는" have strong negative opinion. These terms are in general use and the experiment result seems to be a high probability of opinion polarity. Furthermore, the accuracy of proposed VOC classification model has been compared and the highest classification accuracy of 77.8% is conformed at threshold with -0.50 of opinion classification of VOC. Through the proposed intelligent VOC analyzing system, the real time opinion classification and response priority of VOC can be predicted. Ultimately the positive effectiveness is expected to catch the customer complains at early stage and deal with it quickly with the lower number of staff to operate the VOC system. It can be made available human resource and time of customer service part. Above all, this study is new try to automatic analyzing the unstructured VOC data using opinion mining, and shows that the system could be used as variable to classify the positive or negative polarity of VOC opinion. It is expected to suggest practical framework of the VOC analysis to diverse use and the model can be used as real VOC analyzing system if it is implemented as system. Despite experiment results and expectation, this study has several limits. First of all, the sample data is only collected from a hospital web-site. It means that the sentimental dictionary made by sample data can be lean too much towards on that hospital and web-site. Therefore, next research has to take several channels such as call-center and SNS, and other domain like government, financial company, and education institute.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.1-19
• /
• 2018

Since stock movements forecasting is an important issue both academically and practically, studies related to stock price prediction have been actively conducted. The stock price forecasting research is classified into structured data and unstructured data, and it is divided into technical analysis, fundamental analysis and media effect analysis in detail. In the big data era, research on stock price prediction combining big data is actively underway. Based on a large number of data, stock prediction research mainly focuses on machine learning techniques. Especially, research methods that combine the effects of media are attracting attention recently, among which researches that analyze online news and utilize online news to forecast stock prices are becoming main. Previous studies predicting stock prices through online news are mostly sentiment analysis of news, making different corpus for each company, and making a dictionary that predicts stock prices by recording responses according to the past stock price. Therefore, existing studies have examined the impact of online news on individual companies. For example, stock movements of Samsung Electronics are predicted with only online news of Samsung Electronics. In addition, a method of considering influences among highly relevant companies has also been studied recently. For example, stock movements of Samsung Electronics are predicted with news of Samsung Electronics and a highly related company like LG Electronics.These previous studies examine the effects of news of industrial sector with homogeneity on the individual company. In the previous studies, homogeneous industries are classified according to the Global Industrial Classification Standard. In other words, the existing studies were analyzed under the assumption that industries divided into Global Industrial Classification Standard have homogeneity. However, existing studies have limitations in that they do not take into account influential companies with high relevance or reflect the existence of heterogeneity within the same Global Industrial Classification Standard sectors. As a result of our examining the various sectors, it can be seen that there are sectors that show the industrial sectors are not a homogeneous group. To overcome these limitations of existing studies that do not reflect heterogeneity, our study suggests a methodology that reflects the heterogeneous effects of the industrial sector that affect the stock price by applying k-means clustering. Multiple Kernel Learning is mainly used to integrate data with various characteristics. Multiple Kernel Learning has several kernels, each of which receives and predicts different data. To incorporate effects of target firm and its relevant firms simultaneously, we used Multiple Kernel Learning. Each kernel was assigned to predict stock prices with variables of financial news of the industrial group divided by the target firm, K-means cluster analysis. In order to prove that the suggested methodology is appropriate, experiments were conducted through three years of online news and stock prices. The results of this study are as follows. (1) We confirmed that the information of the industrial sectors related to target company also contains meaningful information to predict stock movements of target company and confirmed that machine learning algorithm has better predictive power when considering the news of the relevant companies and target company's news together. (2) It is important to predict stock movements with varying number of clusters according to the level of homogeneity in the industrial sector. In other words, when stock prices are homogeneous in industrial sectors, it is important to use relational effect at the level of industry group without analyzing clusters or to use it in small number of clusters. When the stock price is heterogeneous in industry group, it is important to cluster them into groups. This study has a contribution that we testified firms classified as Global Industrial Classification Standard have heterogeneity and suggested it is necessary to define the relevance through machine learning and statistical analysis methodology rather than simply defining it in the Global Industrial Classification Standard. It has also contribution that we proved the efficiency of the prediction model reflecting heterogeneity.

• MISULJARYO - National Museum of Korea Art Journal
• /
• v.98
• /
• pp.22-53
• /
• 2020

This paper analyzes the contents, characteristics, and historical significance of the dedicatory inscriptions (josanggi) on the Amitabha Buddha and the Maitreya Bodhisattva statues of Gamsansa Temple, two masterpieces of Buddhist sculpture from the Unified Silla period. In the first section, I summarize research results from the past century (divided into four periods), before presenting a new perspective and methodology that questions the pre-existing notion that the Maitreya Bodhisattva has a higher rank than the Amitabha Buddha. In the second section, through my own analysis of the dedicatory inscriptions, arrangement, and overall appearance of the two images, I assert that the Amitabha Buddha sculpture actually held a higher rank and greater significance than the Maitreya Bodhisattva sculpture. In the third section, for the first time, I provide a new interpretation of two previously undeciphered characters from the inscriptions. In addition, by comparing the sentence structures from the respective inscriptions and revising the current understanding of the author (chanja) and calligrapher (seoja), I elucidate the possible meaning of some ambiguous phrases. Finally, in the fourth section, I reexamine the content of both inscriptions, differentiating between the parts relating to the patron (josangju), the dedication (josang), and the prayers of the patrons or donors (balwon). In particular, I argue that the phrase "for my deceased parents" is not merely a general axiom, but a specific reference. To summarize, the dedicatory inscriptions can be interpreted as follows: when Kim Jiseong's parents died, they were cremated and he scattered most of their remains by the East Sea. But years later, he regretted having no physical memorial of them to which to pay his respects. Thus, in his later years, he donated his estate on Gamsan as alms and led the construction of Gamsansa Temple. He then commissioned the production of the two stone sculptures of Amitabha Buddha and Maitreya Bodhisattva for the temple, asking that they be sculpted realistically to reflect the actual appearance of his parents. Finally, he enshrined the remains of his parents in the sculptures through the hole in the back of the head (jeonghyeol). The Maitreya Bodhisattva is a standing image with a nirmanakaya, or "transformation Buddha," on the crown. As various art historians have pointed out, this iconography is virtually unprecedented among Maitreya images in East Asian Buddhist sculpture, leading some to speculate that the standing image is actually the Avalokitesvara. However, anyone who reads the dedicatory inscription can have no doubt that this image is in fact the Maitreya. To ensure that the sculpture properly embodied his mother (who wished to be reborn in Tushita Heaven with Maitreya Bodhisattva), Kim Jiseong combined the iconography of the Maitreya and Avalokitesvara (the reincarnation of compassion). Hence, Kim Jiseong's deep love for his mother motivated him to modify the conventional iconography of the Maitreya and Avalokitesvara. A similar sentiment can be found in the sculpture of Amitabha Buddha. To this day, any visitor to the temple who first looks at the sculptures from the front before reading the text on the back will be deeply touched by the filial love of Kim Jiseong, who truly cherished the memory of his parents.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.251-273
• /
• 2022

Recently, research on applying text analysis to deep learning has steadily continued. In particular, researches have been actively conducted to understand the meaning of words and perform tasks such as summarization and sentiment classification through a pre-trained language model that learns large datasets. However, existing pre-trained language models show limitations in that they do not understand specific domains well. Therefore, in recent years, the flow of research has shifted toward creating a language model specialized for a particular domain. Domain-specific pre-trained language models allow the model to understand the knowledge of a particular domain better and reveal performance improvements on various tasks in the field. However, domain-specific further pre-training is expensive to acquire corpus data of the target domain. Furthermore, many cases have reported that performance improvement after further pre-training is insignificant in some domains. As such, it is difficult to decide to develop a domain-specific pre-trained language model, while it is not clear whether the performance will be improved dramatically. In this paper, we present a way to proactively check the expected performance improvement by further pre-training in a domain before actually performing further pre-training. Specifically, after selecting three domains, we measured the increase in classification accuracy through further pre-training in each domain. We also developed and presented new indicators to estimate the specificity of the domain based on the normalized frequency of the keywords used in each domain. Finally, we conducted classification using a pre-trained language model and a domain-specific pre-trained language model of three domains. As a result, we confirmed that the higher the domain specificity index, the higher the performance improvement through further pre-training.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.227-252
• /
• 2018

The evolution of instant communication has mirrored the development of the Internet and messenger applications are among the most representative manifestations of instant communication technologies. In messenger applications, senders use emoticons to supplement the emotions conveyed in the text of their messages. The fact that communication via messenger applications is not face-to-face makes it difficult for senders to communicate their emotions to message recipients. Emoticons have long been used as symbols that indicate the moods of speakers. However, at present, emoticon-use is evolving into a means of conveying the psychological states of consumers who want to express individual characteristics and personality quirks while communicating their emotions to others. The fact that companies like KakaoTalk, Line, Apple, etc. have begun conducting emoticon business and sales of related content are expected to gradually increase testifies to the significance of this phenomenon. Nevertheless, despite the development of emoticons themselves and the growth of the emoticon market, no suitable emoticon recommendation system has yet been developed. Even KakaoTalk, a messenger application that commands more than 90% of domestic market share in South Korea, just grouped in to popularity, most recent, or brief category. This means consumers face the inconvenience of constantly scrolling around to locate the emoticons they want. The creation of an emoticon recommendation system would improve consumer convenience and satisfaction and increase the sales revenue of companies the sell emoticons. To recommend appropriate emoticons, it is necessary to quantify the emotions that the consumer sees and emotions. Such quantification will enable us to analyze the characteristics and emotions felt by consumers who used similar emoticons, which, in turn, will facilitate our emoticon recommendations for consumers. One way to quantify emoticons use is metadata-ization. Metadata-ization is a means of structuring or organizing unstructured and semi-structured data to extract meaning. By structuring unstructured emoticon data through metadata-ization, we can easily classify emoticons based on the emotions consumers want to express. To determine emoticons' precise emotions, we had to consider sub-detail expressions-not only the seven common emotional adjectives but also the metaphorical expressions that appear only in South Korean proved by previous studies related to emotion focusing on the emoticon's characteristics. We therefore collected the sub-detail expressions of emotion based on the "Shape", "Color" and "Adumbration". Moreover, to design a highly accurate recommendation system, we considered both emotion-technical indexes and emoticon-emotional indexes. We then identified 14 features of emoticon-technical indexes and selected 36 emotional adjectives. The 36 emotional adjectives consisted of contrasting adjectives, which we reduced to 18, and we measured the 18 emotional adjectives using 40 emoticon sets randomly selected from the top-ranked emoticons in the KakaoTalk shop. We surveyed 277 consumers in their mid-twenties who had experience purchasing emoticons; we recruited them online and asked them to evaluate five different emoticon sets. After data acquisition, we conducted a factor analysis of emoticon-emotional factors. We extracted four factors that we named "Comic", Softness", "Modernity" and "Transparency". We analyzed both the relationship between indexes and consumer attitude and the relationship between emoticon-technical indexes and emoticon-emotional factors. Through this process, we confirmed that the emoticon-technical indexes did not directly affect consumer attitudes but had a mediating effect on consumer attitudes through emoticon-emotional factors. The results of the analysis revealed the mechanism consumers use to evaluate emoticons; the results also showed that consumers' emoticon-technical indexes affected emoticon-emotional factors and that the emoticon-emotional factors affected consumer satisfaction. We therefore designed the emoticon recommendation system using only four emoticon-emotional factors; we created a recommendation method to calculate the Euclidean distance from each factors' emotion. In an attempt to increase the accuracy of the emoticon recommendation system, we compared the emotional patterns of selected emoticons with the recommended emoticons. The emotional patterns corresponded in principle. We verified the emoticon recommendation system by testing prediction accuracy; the predictions were 81.02% accurate in the first result, 76.64% accurate in the second, and 81.63% accurate in the third. This study developed a methodology that can be used in various fields academically and practically. We expect that the novel emoticon recommendation system we designed will increase emoticon sales for companies who conduct business in this domain and make consumer experiences more convenient. In addition, this study served as an important first step in the development of an intelligent emoticon recommendation system. The emotional factors proposed in this study could be collected in an emotional library that could serve as an emotion index for evaluation when new emoticons are released. Moreover, by combining the accumulated emotional library with company sales data, sales information, and consumer data, companies could develop hybrid recommendation systems that would bolster convenience for consumers and serve as intellectual assets that companies could strategically deploy.