• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.3
• /
• pp.336-340
• /
• 2008

Sentiment classification is a recent subdiscipline of text classification, which is concerned not with the topic but with opinion. In this paper, we present a Korean sentence and document classification system using effective sentiment features. Korean sentiment classification starts from constructing effective sentiment feature sets for positive and negative. The synonym information of a English word thesaurus is used to extract effective sentiment features and then the extracted English sentiment features are translated in Korean features by English-Korean dictionary. A sentence or a document is represented by using the extracted sentiment features and is classified and evaluated by SVM(Support Vector Machine).

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.4
• /
• pp.83-88
• /
• 2013

Many studies adopting brain functions to the engineering systems have been made for recent years as the brain Science has developed. If we investigate the parts which take part in memorizing and emotional process, we can know that Hippocampus of memorizing center and Amygdala of Emotional center closely cooperate each other. Actually Knowledge effects on Emotion and Emotion effects on Knowledge. During the human decision making, emotional factor has much important effects on Decision making process. For implementing more delicate intelligent system, the knowledge base coupled to emotional factor should be designed. Accordingly in this paper starting from the idea of cooperating system between Hippocampus and Amygdala,, we design Knowledge Emotion Binding System and propose Emotional changing mechanism by Memory retrieval and knowledge reasoning process.

• Journal of KIISE:Software and Applications
• /
• v.31 no.6
• /
• pp.799-807
• /
• 2004

In this paper, we deal with an emotion recognition method using facial images and speech signal. Six basic human emotions including happiness, sadness, anger, surprise, fear and dislike are investigated. Emotion recognition using the facial expression is performed by using a multi-resolution analysis based on the discrete wavelet transform. And then, the feature vectors are extracted from the linear discriminant analysis method. On the other hand, the emotion recognition from speech signal method has a structure of performing the recognition algorithm independently for each wavelet subband and then the final recognition is obtained from a multi-decision making scheme.

• Proceedings of the Korea Contents Association Conference
• /
• 2019.05a
• /
• pp.345-346
• /
• 2019

SNS의 다양한 역기능과 함께 중독문제가 사회적 문제로 대두되고 있는 가운데 이미지 기반의 인스타그램이 강세를 보인다. 이에 본 연구는 SNS중에서 이용도가 높은 인스타그램 사용제한 시 사용자의 감정에 미치는 영향과 대안 활동을 파악하기 위한 목적으로 수행되었다. 실험 방법은 인스타그램 1일 5회 이상 이용자 3명을 대상으로 7일간 앱 삭제 및 이용을 제한하고 매일 1인칭 관찰기법인 자기 일기 작성으로 감정변화와 대안 활동을 수집했다. 본 연구의 결과는 사용 빈도수가 높을수록 시간이 흘러도 부정적 감정이 감소하지 않았고 사용 빈도수가 낮을수록 부정적 감정이 점차 감소하였다. 대안 활동으로는 오프라인 활동보다는 온라인 활동이 많았고 여러 종류의 스마트폰 미디어 활동을 한 것으로 나타났다. 이 연구는 나아가 의존도에 따라 부정적 감정소강 소요 시간을 측정하는 연구로 발전될 것을 기대하며 이에 따라 SNS중독성 해결에 필요한 시간, 대안 활동 제시의 연구 초석이 되길 기대한다.

• Journal of KIISE:Software and Applications
• /
• v.36 no.6
• /
• pp.491-497
• /
• 2009

This paper proposes a new feature weighting method for document sentiment classification. The proposed method considers the difference of sentiment intensities among sentences in a document. Sentiment features consist of sentiment vocabulary words and the sentiment intensity scores of them are estimated by the chi-square statistics. Sentiment intensity of each sentence can be measured by using the obtained chi-square statistics value of each sentiment feature. The calculated intensity values of each sentence are finally applied to the TF-IDF weighting method for whole features in the document. In this paper, we evaluate the proposed method using support vector machine. Our experimental results show that the proposed method performs about 2.0% better than the baseline which doesn't consider the sentiment intensity of a sentence.

• The Journal of the Korea Contents Association
• /
• v.14 no.5
• /
• pp.85-94
• /
• 2014

This study examined the characteristics of movie reviews based on emotional expressions, using the structural analysis. Major results were as follows; firstly, the most cited emotional expression was 'fun'. Fun was the important discriminator for evaluating movies. Secondly, cluster analysis results found that although Korean movies were clustered by many emotional expressions such as fun, immersion and impression, foreign movies were grouped by joust an emotional expression including fun. Internet users tended to divide foreign movie into two kinds of movies such as fun movie and boring movies.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.25 no.3
• /
• pp.101-118
• /
• 2014

Given the context of rapid developing ubiquitous computing environment, it is imperative for users to search and use images based on affective meanings. However, it has been difficult to index affective meanings of image since emotions of image are substantially subjective and highly abstract. In addition, utilizing low level features of image for indexing affective meanings of image has been limited for high level concepts of image. To facilitate the access points of affective meanings of image, this study aims to utilize user-provided responses of images. For a data set, emotional words are collected and cleaned from twenty participants with a set of fifteen images, three images for each of basic emotions, love, sad, fear, anger, and happy. A total of 399 unique emotion words are revealed and 1,093 times appeared in this data set. Through co-word analysis and network analysis of emotional words from users' responses, this study demonstrates expanded word sets for five basic emotions. The expanded word sets are characterized with adjective expression and action/behavior expression.

• KIISE Transactions on Computing Practices
• /
• v.21 no.2
• /
• pp.160-165
• /
• 2015

Traditional speech emotion recognition techniques recognize emotions using a general training model based on the voices of various people. These techniques can not consider personalized speech character exactly. Therefore, the recognized results are very different to each person. This paper proposes an adaptive speech emotion recognition framework made from user's' immediate feedback data using a prompted labeling technique for building a personal adaptive recognition model and applying it to each user in a mobile device environment. The proposed framework can recognize emotions from the building of a personalized recognition model. The proposed framework was evaluated to be better than the traditional research techniques from three comparative experiment. The proposed framework can be applied to healthcare, emotion monitoring and personalized service.

• Journal of KIISE:Software and Applications
• /
• v.37 no.4
• /
• pp.317-322
• /
• 2010

This paper proposes how to improve performance of the Korean document sentiment-classification system using semantic properties of the sentiment words. A sentiment word means a word with sentiment, and sentiment features are defined by a set of the sentiment words which are important lexical resource for the sentiment classification. Sentiment feature represents different sentiment intensity in general field and in specific domain. In general field, we can estimate the sentiment intensity using a snippet from a search engine, while in specific domain, training data can be used for this estimation. When the sentiment intensity of the sentiment features are estimated, it is called semantic orientation and is used to estimate the sentiment intensity of the sentences in the text documents. After estimating sentiment intensity of the sentences, we apply that to the weights of sentiment features. In this paper, we evaluate our system in three different cases such as general, domain-specific, and general/domain-specific semantic orientation using support vector machine. Our experimental results show the improved performance in all cases, and, especially in general/domain-specific semantic orientation, our proposed method performs 3.1% better than a baseline system indexed by only content words.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2001.11a
• /
• pp.87-90
• /
• 2001

본 연구에서는 감성 평가 시스템에 가장 적합한 파라미터를 찾기 위하여 3가지 뇌파 파라미터를 이용하여 감정 분류 실험을 하였다. 뇌파 파라미터는 선형예측기계수(linear predictor coefficients)와 FFT 스펙트럼 및 AR 스펙트럼의 밴드별 상호상관계수(cross-correlation coefficients)를 이용하였으며, 감정은 relaxation, joy, sadness, irritation으로 설정하였다. 뇌파 데이터는 대학의 연극동아리 학생 4명을 대상으로 수집하였으며, 전극 위치는 Fp1, Fp2, F3, F4, T3, T4, P3, P4, O1, O2를 사용하였다. 수집된 뇌파 데이터는 전처리를 거친 후 특징 파라미터를 추출하고 패턴 분류기로 사용된 신경회로망(neural network)에 입력하여 감정 분류를 하였다. 감정 분류실험 결과 선형예측기계수를 이용하는 것이 다른 2가지 보다 좋은 성능을 나타내었다.