• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.1
• /
• pp.17-24
• /
• 2020

In this paper, we present a movie rating prediction architecture based on a convolutional neural network (CNN). Our prediction architecture extends TextCNN, a popular CNN-based architecture for sentence classification, in three aspects. First, character embeddings are utilized to cover many variants of words since reviews are short and not well-written linguistically. Second, the attention mechanism (i.e., squeeze-and-excitation) is adopted to focus on important features. Third, a scoring function is proposed to convert the output of an activation function to a review score in a certain range (1-10). We evaluated our prediction architecture on a movie review dataset and achieved a low MSE (e.g., 3.3841) compared with an existing method. It showed the superiority of our movie rating prediction architecture.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.6
• /
• pp.1225-1235
• /
• 2010

The coarse classifying procedure in credit scoring splits the values of a continuous characteristic into bands and the values of a discrete characteristic into groups of values. Also, the scorecard degrades over time and thus we should adjust the cut-off score being used. However, the coarse classifying and the adjustment of cut-off score in credit scoring are very complicate and troublesome procedure. Thus, in this paper, we develop a software for the coarse classifying and the model evaluation by using Visual Basic Language. By using the developed software, we can find the best split in the coarse classifying and the optimal cut-off score in the model evaluation.

• Journal of Internet Computing and Services
• /
• v.16 no.2
• /
• pp.41-48
• /
• 2015

On movie review sites, movie ratings are determined by netizens' subjective judgement. This means that inconsistency between ratings and opinions from netizens often occurs. To solve this problem, this paper proposes sentiment sentence sets which affect movie evaluation, and apply sets to comments to infer ratings. Creation of sentiment sentence sets is consisted of two stages, construction of sentiment word dictionary and creation of sentiment sentences for sentiment estimation. Sentiment word dictionary contains sentimental words and its polarities included in reviews. Elements of sentiment sentences are combined with movie related noun and predicate from words sentiment word dictionary. In this study, to make correspondence between polarity of sentiment sentence and sentiment word dictionary, sentiment sentences which have different polarity with sentiment word dictionary are removed. The scores of comments are calculated by applying averages of sentiment sentences elements. The result of experiment shows that sentence scores from sentiment sentence sets are closer to reflect real opinion of comments than ratings by netizens'.

• The Journal of Society for e-Business Studies
• /
• v.22 no.1
• /
• pp.65-87
• /
• 2017

We propose a method to analyze the user reviews and ratings of the products in the online shopping mall and automatically extracts the features of the products to determine the characteristics of a product. By judging whether a rating is given by a specific feature of a product, our method distributes the score to each feature. Conventional methods force users to wastes time reading overflowing number of reviews and ratings to decide whether to buy the product or not. Moreover, it is difficult to grasp the merits and demerits of the product, because of the way reviews and ratings are provided. It is structured in a way that it is impossible to decide which rating is given to the which characteristics of the product. Therefore, in this paper, to resolve this problem, we propose a method to automatically extract the feature of the product from the user review and distribute the score to appropriate characteristics of the product by calculating the rating of each feature from the overall rating. proposed method collects product reviews and ratings, conducts morphological analysis, and extracts features and emotional words of the products. In addition, a method for determining the polarity of a sentence in which the feature appears is given a weight value for each feature. results of the experiment and the questionnaires comparing the existing methods show the usefulness of the proposed method. We also validates the results by comparing the analysis conducted by the product review experts.

• The Journal of the Korea Contents Association
• /
• v.18 no.5
• /
• pp.367-375
• /
• 2018

The study aims to determine which groups leave longer(more active) online reviews(comments) on the film by separating groups, one that satisfied with the movie while the other group dissatisfied with the movie. The data used were rating scores and reviews(comments) from Naver Movie API, and break-even point data provided by Korea Film Commission. We analyzed the relationship between movie rating and review length, before and after movie opening, the characteristics of review length according to the box office, and whether the movie rating affects the review length.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2007.11a
• /
• pp.163-166
• /
• 2007

본 연구에서는 우수 학생을 알아보기 위해 학생들의 학습 성과 및 과외활동을 바탕으로 평가모형을 설계하고 AHP(Analytic Hierarchy Process) 기법을 통해 분석하였다. 대부분의 대학에서 시행되고 있는 장학금 제도는 평가 기준이 해당 학기 평점으로 장학금 혜택을 받는 학생들이 일부 학생으로 제한되는 경우가 생기기도 한다. 실제로 평점뿐 아니라 다른 평가 기준을 가지고 학생들을 평가하여 학생들의 다양한 특성을 키워 줄 필요가 있다 평점만으로 학생을 평가하는 방식이 아닌 다양한 기준의 평가 모형을 가지고 학생들을 평가하는 새로운 방식의 학생평가모델을 제안하고자 한다.

• The Korean Journal of Applied Statistics
• /
• v.13 no.1
• /
• pp.11-18
• /
• 2000

대학의 학업성취도를 나타내는 평점평균은 많은 요인의 영향을 받는 것으로 알려져 있다. 본 논문은 형행입시제도하에서 획득 가능한 요인과 평점평균과의 관련성을 일반 화선형모형(GLM)을 이용하여 통계적으로 분석·평가하고자 한다. 여기서 얻어진 경과는 요즈음 변화가 모색되고 있는 입시제도나 대학교육제도의 개선에 적으나마 도움이 되는 기초자료를 제공할 수 있으리라 믿어진다. 분석자료는 1996, 97학년도 인제대학교에 입학한 학생들의 입시자료와 96,97학년도의 평점평균, 기숙사입사 여부 등을 대상으로 삼았다.

• 한국데이터정보과학회:학술대회논문집
• /
• 2006.04a
• /
• pp.191-194
• /
• 2006

대학에서 학생 개인의 학업성취도를 나타내는 평점평균(GPA)은 많은 요인의 영향을 받는 것으로 알려져 있다. 본 연구에서는 현행입시제도하에서 획득 가능한 자료를 이용하여 학생부 성적과 수학능력시험성적이 대학의 학업성취도를 나타내는 평점평균과 어떠한 관계를 갖고 있는지 일반화선형모형(GLM)을 이용하여 통계적으로 분석 평가하고자 한다. 여기서 얻어진 결과는 2008학년도부터 적용되는 제7차 교육과정의 수학능력시험성적과 학생부 성적 반영 비율 산정에 필요한 기초적 정보를 제공하는데 도움이 될 수 있으리라 믿어진다. 분석에 사용한 자료는 2003, 2004학년도 인제대학교에 입학한 학생들의 입학성적과 2003, 04, 05학년도의 평점평균을 대상으로 삼았다.

• Proceedings of the Korea Contents Association Conference
• /
• 2012.05a
• /
• pp.325-326
• /
• 2012

세 얼간이는 국내 포탈 사이트에 평점 등록한 네티즌만 2만여 명이 넘었으며, 네이버 9.43, 다음 9.7, 네이트 9.5 등의 평점으로 역대 영화 평점 순위 1위를 차지했다. 반지의 제왕 같은 판타지 블록버스터, 타이타닉, 대부 등 세계적인 흥행으로 전설이 되어버린 작품들의 기록을 뛰어넘는 것으로 전 세계 부동의 흥행 1위 아바타를 뛰어넘고, 700억 원이 넘는 수익을 창출했다. 세 얼간이가 성공할 수 있었던 것은 몇 가지로 볼 수 있는데 영화 전편에 걸친 스토리텔링과 비선형적 스토리구성, 모션의 활용, 사운드의 활용, 이벤트의 활용 등 인터랙션과 스토리텔링의 효과가 우수하였다고 사료한다.

• The Korean Journal of Applied Statistics
• /
• v.22 no.2
• /
• pp.309-315
• /
• 2009

The degree of the impression about a special commodity in the internet shopping malls depends on the evaluation and the corresponding rating of customers who purchased and used this commodity. We can find the problems in online ratings system of Korean internet shopping malls and suggest the simple solutions.