• Journal of the Korea Society of Computer and Information
• /
• v.17 no.9
• /
• pp.39-47
• /
• 2012

The opinion of user on a certain product is expressed in positive/negative sentiments for specific features of it. In some cases, they are expressed for a holistic part of homogeneous specific features, or expressed for product itself. Therefore, in the area of opinion mining, name of opinion features to be extracted are specific feature names, holonyms for theses specific features, and product names. However, when the opinion target is described with product name or holonym, sometimes it may not match feature name of opinion sentence to true opinion target intended by the reviewer. In this paper, we present a method to extract opinion targets from opinion sentences. Most importantly, we propose a method to extract true target from the feature names mismatched to a intended target. First, we extract candidate opinion pairs using dependency relation between words, and then select feature names frequently mismatched to opinion target. Each selected opinion feature name is replaced to a specific feature intended by the reviewer. Finally, in order to extract relevant opinion features from the whole candidate opinion pairs including modified opinion feature names, candidate opinion pairs are rearranged by the order of user's interest.

• Sijohaknonchong
• /
• v.42
• /
• pp.93-115
• /
• 2015

Dynamics of Sijo was regarded as a genre of 'closed nature' once. But ironically thanks to the 'closed nature', today dynamics of Sijo is refocused in diverse fields. Sijo is quoted not only in its original field of literature, but also in writing study. Quite remarkably, it is often referred to in the field of literary therapy, further in emotional healing. This article discussed the dynamics of Sijo as a manifestation of emotion especially called Gamsung in the process of the refocus. It is to show effectively that as a literary genre, Sijo can interact and share what is reasonal as well as what is emotional and sentimental in a poem as an emotional container beyond the lyricism Sijo has. Of course, it is also clear that the concept of lyricism may limit the dynamics of Sijo itself. Thus, the key word 'Gamsung' mainly referred to in this article was used to show the dynamics which Sijo has as much as possible, overcoming the limitation. That is, the purpose of the study is to prove that Sijo is the genre to represent human emotion most dynamically by reviewing the reasonal aspect of Sijo in addition to its emotional disposition which has been estimated to focus on sentiment or emotion. In the process of reinterpreting the structure of Sijo, the specific analysis on such emotional disposition and reasonal aspect was conducted by structurizing that as '(1) Facing, (2) Feeling dynamical, (3) Interpellating by feeling, and (4) feeling by sensation'.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.6
• /
• pp.1361-1369
• /
• 2014

This research is for analyzing the change rate of housing rent price index produced by KAB (Korea Appraisal Board) in the monthly periodical, Survey on Housing Monthly Rent. The index is a very important and useful indicator to understand and diagnose the house rental market. However, the index is criticized in that it tends to decline when the price level of Jeonse (i.e., a typical type of dwellings in Korea, generally leased on a deposit basis for 1 or 2 years) is highly going up, which is inconsistent with the actual economic sentiment of tenants. We verify the reason why such phenomenon occurs and suggest a simple but novel method to analyze properly the change rate of the index. The main findings are as follows. The key factor to trigger the problem is the use of the conversion rate for Jeonse-to-monthly rent for constructing the rent price indexes. We separate the effect of the conversion rate out of the change rate of the index and quantify the adjusted real change rate showing an increase of the rent price level which is masked by the conversion rate before.

• 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 Digital Convergence
• /
• v.17 no.2
• /
• pp.163-170
• /
• 2019

Over the past decade, the development of the Web explosively increased the data. Feature selection step is an important step in extracting valuable data from a large amount of data. This study proposes a novel opinion mining model based on combining feature selection (FS) methods with Word embedding to vector (Word2vec) and BOW (Bag-of-words). FS methods adopted for this study are CFS (Correlation based FS) and IG (Information Gain). To select an optimal FS method, a number of classifiers ranging from LR (logistic regression), NN (neural network), NBN (naive Bayesian network) to RF (random forest), RS (random subspace), ST (stacking). Empirical results with electronics and kitchen datasets showed that LR and ST classifiers combined with IG applied to BOW features yield best performance in opinion mining. Results with laptop and restaurant datasets revealed that the RF classifier using IG applied to Word2vec features represents best performance in opinion mining.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.1
• /
• pp.85-92
• /
• 2022

In order to identify the factors and problems in which military sexual violence is a continuous and repeated blind spot, this study conducted a content analysis focusing on articles of military sexual violence incidents covered in Internet news from January 2010 to June 15, 2021. carried out. As a result of the study, structurally unequal power relations, authoritarian and closed military organizational culture, internal military response system that is distrustful of passive responses to sexual violence, and enveloping family-friendly investigations and tolerant punishment of perpetrators are blind spots despite the Ministry of National Defense's efforts to improve. factors that exist. Underlying this, the compensatory spirit caused by the conscription system and the negative effects of the patriarchal system are embodied in the national sentiment, suggesting that the sense of crisis of division and an overly permissive attitude toward the military act as a factor that slows change. As an improvement plan according to the results, it is necessary to entail the establishment of a civilian-centered judicial institution, strong punishment of perpetrators, and limited pension payment, as well as honorable punishment such as 'class demotion' in the military culture with a clear hierarchical relationship. Taken together, we can see that most military sexual violence is caused by a hierarchy, and it strongly suggests that the main cause of sexual violence is unequal power relations.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.4
• /
• pp.435-444
• /
• 2022

There are three focuses in the paper. Firstly, the study identified what channels were most viewed by YouTube users to watch the 'Daejang-dong scandal,' which was the most powerful agenda to influence the candidate preference among voters during the 20th presidential election. Secondly, the study analyzed whether the political tone of the first videos was in line with that of the subsequent videos. Finally, we compared the sentiment of comments on the first and subsequent videos. The results showed that TBS 'News Factory' and 'TV Chosun News' represented liberal and conservative factions, respectively. Secondly, the political tone of channels that were viewed subsequently was neutral, but the conservative channel users left more negative comments and that was significant statistically. In addition, about 80% of the conservative and liberal channel users shared the same political tendency with the channel they watched first, and more than 90% of the comments left at the subsequent videos in line with that of at the first news. Based on these results, the study concluded that the voters tended to seek political news that was similar with their political ideology, and it was considered a sort of echo chamber phenomenon on the YouTube. The study suggests that the performance of high-quality journalism by traditional news outlet might contribute to decrease the negative influence of political contents on YouTube users.

• The Journal of the Korea Contents Association
• /
• v.22 no.1
• /
• pp.214-223
• /
• 2022

The purpose of this study is to present a new industrial land demand prediction method that can consider external economic factors. The analysis model used ARIMA-X, which can consider exogenous variables. Exogenous variables are composed of macroeconomic variable, Business Survey Index, and Composite Economic Index variables to reflect the economic and industrial structure. And, among the exogenous variables, only variables that precede the supply of industrial land are used for prediction. Variables with precedence in the supply of industrial land were found to be import, private and government consumption expenditure, total capital formation, economic sentiment index, producer's shipment index, machinery for domestic demand and composite leading index. As a result of estimating the ARIMA-X model using these variables, the ARIMA-X(1,1,0) model including only the import was found to be statistically significant. The industrial land demand forecast predicted the industrial land from 2021 to 2030 by reflecting the scenario of change in import. As a result, the future demand for industrial land was predicted to increase by 1.91% annually to 1,030.79 km². As a result of comparing these results with the existing exponential smoothing method, the results of this study were found to be more suitable than the existing models. It is expected to b available as a new industrial land forecasting model.

• 지역과문화
• /
• v.8 no.3
• /
• pp.27-48
• /
• 2021

In recent years, China's tourism performing art in a series of new completion of the project, increase the box office of tourism performing arts industry, higher economic income, at the same time led to the formation of brand of tourism performing arts and has a good reputation, with the regional culture, has a certain role in promoting economic development, including Large scenario experience drama is one of the key projects. Large scenario experience drama is a new form of drama that simulates the space design of real environment and enables the audience to have active experience in visual, auditory, smell, taste, touch and other senses with strong interactivity.Large scenario experience drama are adapted from traditional Chinese culture, regional culture and long-passed stories, and combine high technology such as lighting, sound effects, special effects and 3D effects to make the audience's experience more real.As the first Large scenario experience drama in China, 'You Jian Ping-yao' reflects the profound culture of Shanxi with new forms of expression and creative means, in the form of scene experience and make the audience more intuitive feel the 'Shanxi emotion', 'Shanxi sentiment' and 'Shanxi Morality', carry forward the traditional culture at the same time, also passed the Shanxi ancient and great values, strengthened the drama of China's movie village, impetus the development of the tourism industry in Shanxi, drive the Shanxi region of jingjing, gradually formed a complete industrial chain. However, there are also limitations such as improper plot connection and improper tourist management, which can improve the performance effect through more audience interaction and guidance. Therefore, it can be seen that large-scale situational experience dramas play a great role in promoting the dissemination of traditional culture and values, the development of tourism industry, the formation of regional brand characteristics and economic development. Through these, it can be seen that large-scale situational experience plays have enlightenments such as innovative thinking content, gradually forming an industrial chain closed-loop, and broadening publicity channels for the development of live-action performances.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.309-323
• /
• 2023

As the role of online reviews has become increasingly crucial, numerous studies have been conducted to utilize helpful reviews. Helpful reviews, perceived by customers, have been verified in various research studies to be influenced by factors such as ratings, review length, review content, and so on. The determination of a review's helpfulness is generally based on the number of 'helpful' votes from consumers, with more 'helpful' votes considered to have a more significant impact on consumers' purchasing decisions. However, recently written reviews that have not been exposed to many customers may have relatively few 'helpful' votes and may lack 'helpful' votes altogether due to a lack of participation. Therefore, rather than relying on the number of 'helpful' votes to assess the helpfulness of reviews, we aim to classify them based on review content. In addition, the text of the review emerges as the most influential factor in review helpfulness. This study employs text mining techniques, including topic modeling and sentiment analysis, to analyze the diverse impacts of content and emotions embedded in the review text. In this study, we propose a review helpfulness prediction model based on review content, utilizing movie reviews from IMDb, a global movie information site. We construct a review helpfulness prediction model by using an explainable Graph Neural Network (GNN), while addressing the interpretability limitations of the machine learning model. The explainable graph neural network is expected to provide more reliable information about helpful or non-helpful reviews as it can identify connections between reviews.