• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.628-631
• /
• 2023

We present a new approach to evaluate the generated texts by Large Language Models (LLMs) for meme classification. Analyzing an image with embedded texts, i.e. meme, is challenging, even for existing state-of-the-art computer vision models. By leveraging large image-to-text models, we can extract image descriptions that can be used in other tasks, such as classification. In our methodology, we first generate image captions using BLIP-2 models. Using these captions, we use GPT-4 to evaluate the relationship between the caption and the meme text. The results show that OPT_6.7B provides a better rating than other LLMs, suggesting that the proposed method has a potential for meme classification.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.2
• /
• pp.202-207
• /
• 2010

In this paper, we present an automatic sentiment classification method for on-line movie reviews that do not contain explicit sentiment rating scores. For the sentiment polarity classification, positive or negative, we use a Support Vector Machine classifier based on syllable kernel that is an extended model of string kernel. We give some experimental results which show that proposed syllable kernel model can be effectively used in sentiment classification tasks for on-line movie reviews that usually contain a lot of grammatical errors such as spacing or spelling errors.

• The Journal of Information Systems
• /
• v.29 no.3
• /
• pp.145-157
• /
• 2020

Purpose This study proposed an approach for predicting the efficiency rating of the cultural tourism festivals using DEA and machine learning techniques. The cultural tourism festivals are selected for the best festivals through peer reviews by tourism experts. However, only 10% of the festivals which are held in a year could be evaluated in the view of effectiveness without considering the efficiency of festivals. Design/methodology/approach Efficiency scores were derived from the results of DEA for the prediction of efficiency ratings. This study utilized BCC models to reflect the size effect of festivals and classified the festivals into four ratings according the efficiency scores. Multi-classification method were considered to build the prediction of four ratings for the festivals in this study. We utilized neural networks and SVMs with OAO(one-against-one), OAR(one-against-rest), C&S(crammer & singer) with Korea festival data from 2013 to 2018. Findings The number of total visitors in low efficient rating of DEA is more larger than the number of total visitors in high efficient ratings although the total expenditure of visitors is the highest in the most efficient rating when we analyzed the results of DEA for the characteristics of four ratings. SVM with OAO model showed the most superior performance in accuracy as SVM with OAR model was not trained well because of the imbalanced distribution between efficient rating and the other ratings. Our approach could predict the efficiency of festivals which were not included in the review process of culture tourism festivals without rebuilding DEA models each time. This enables us to manage the festivals efficiently with the proposed machine learning models.

• Journal of Digital Contents Society
• /
• v.15 no.4
• /
• pp.559-568
• /
• 2014

Previous polarity classification using sentiment analysis utilizes a sentence rule by product reviews based rating points. It is difficult to be applied to blogs which have not rating of product reviews and is possible to fabricate product reviews by comment part-timers and managers who use web site so it is not easy to understand a product and store reviews which are reliability. Considering to these problems, if we analyze blogs which have personal and frank opinions and classify polarity, it is possible to understand rightly opinions for the product, store. This paper suggests that we extract high frequency vocabularies in blogs by several domains and choose topic words. Then we apply a technique of sentiment analysis and classify polarity about contents of blogs. To evaluate performances of sentiment analysis, we utilize the measurement index that use Precision, Recall, F-Score in an information retrieval field. In a result of evaluation, using suggested sentiment analysis is the better performances to classify polarity than previous techniques of using the sentence rule based product reviews.

• Health Policy and Management
• /
• v.33 no.3
• /
• pp.295-310
• /
• 2023

Background: The long-term care (LTC) group has higher rates of chronic disease and disability registration compared to the general older people population. There is a need to provide integrated medical services and care for LTC group. Consequently, this study aimed to identify medical usage patterns based on the ratings of LTC and the characteristics of benefits usage in the LTC group. Methods: This study employed the National Health Insurance Service Database to analyze the effects of demographic and LTC-related characteristics on medical usage from 2015 to 2019 using a repeated measures analysis. A longitudinal logit model was applied to binary data, while a linear mixed model was utilized for continuous data. Results: In the case of LTC ratings, a positive correlation was observed with overall medical usage. In terms of LTC benefit usage characteristics, a higher overall level of medical usage was found in the group using home care benefits. Detailed analysis by medical institution classification revealed a maintained correlation between care ratings and the volume of medical usage. However, medical usage by classification varied based on the characteristics of LTC benefit usage. Conclusion: This study identified a complex interaction between LTC characteristics and medical usage. Predicting the requisite medical services based on the LTC rating presented a challenge. Consequently, it becomes essential for the LTC group to continuously monitor medical and care needs, even after admission into the LTC system. To facilitate this, it is crucial to devise an LTC rating system that accurately reflects medical needs and to broaden the implementation of integrated medical-care policies.

• Journal of Korean Association for Spatial Structures
• /
• v.24 no.3
• /
• pp.69-77
• /
• 2024

The purpose of this study is to present a plan for reducing noise between floors of apartment houses in Korea and to examine the method for evaluating noise blocking performance rating between floors. The definition of floor noise and classification method of floor noise can be described, and floor noise can be distinguished into lightweight impact sound and heavy impact sound. The wall-type structure, which is mainly adopted in domestic apartments, relatively transmits vibration caused by impact sources rather than using columns and beams, so noise problems between floors are relatively higher than systems using columns and beams. Three representative methods for reducing and blocking floor noise are described, and criteria for evaluating the effectiveness of floor noise reduction by each method are described. In addition, the method for noise reduction and blocking grades for each construction method currently applied in Korea was described, and as a result, it was judged that the domestic rating evaluation method was not suitable for the current domestic situation, and a new evaluation method and standard were needed.

• Tunnel and Underground Space
• /
• v.5 no.4
• /
• pp.308-317
• /
• 1995

The stability study on the rock slope where have produced failures in Boryung dam site was evaluated using the streonet analysis techniques. SMR(Slope Mass Rating) approach which is suitable for preliminary assessment of slope stability in rock was also carried out for rating rock mass. The 3-4 major discontinuity sets are distributed and all type of failure(plane, wedge and toppling failure) are presented in this slope face. The dip of slope must be lowered to friction angle(26degree), otherwise the possibility of plane and toppling faiue will always exist in this slope.

• Proceedings of the Korean Geotechical Society Conference
• /
• 1993.03a
• /
• pp.33-40
• /
• 1993

The Bieniawski's geomechanics classification system(1984) is widely employed as a tool of engineering evaluation of rock masses for tunnel design. Since the siz parameters adoped in the system are believed to control the engineering behavior of rock mass under an external load, no question may be raised to the conceptional idea immanent in the system. However, the rating grade for each individual parameter given in the system may be properly measured since an engineering property of rock mass is not stepwise changed but continuously changed. In order to get the proper rating grade based upon the continuously changed properties in each parameter, several equations presented in this paper are obtained through regration analyses with the grades and median values of properties givne in the system. A FORTRAN computer program given in the paper could provide not only RMR value but also rock mass properties (E, c, o, v, etc.) using the empirical equations.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2003.11a
• /
• pp.864-869
• /
• 2003

KS F 2808 was revised in 2000 and KS F 2862-1 was newly established in 2001. Thus Related Korean Industrial Standard such as KS F 4724, KS F 4735, KS F 4736 should be revised according to KS F 2808 and KS F 28612-1. This study aims to elicit the new rating numbers such as R$\sub$w/, R$\sub$w/＋C, R$\sub$w/＋C$\sub$tr/, L$\sub$m/ defined in KS F 2862-1 instead of exiting rating number; transmission loss of 500Hz.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.14 no.7
• /
• pp.626-631
• /
• 2004

In this study, the extracted words from the former study such as annoying, loud, noisy, irritating, disagreeable, strident, disturbed, and dissonant are given to subjects in psycho acoustic experiment lab. And then, correlation analysis between the words and floor impact noise rating method were carried out. As a result of this study followings are suggested ‘Annoying’ is the word most accurately expressing the subjects’ unpleasant feeling of domestic floor impact noise. The results of this study could be basic materials for psycho acoustic experiments for criteria on floor impact noise and Sound Classification on Floor Impact Sound Insulation Performance.