• The KIPS Transactions:PartB
• /
• v.18B no.5
• /
• pp.325-332
• /
• 2011

Social Network Services(SNS) such as Twitter, Facebook and Myspace have gained popularity worldwide. Especially, sentiment analysis of SNS users' sentence is very important since it is very useful in the opinion mining. In this paper, we propose a new sentiment classification method of sentences which contains formal and informal vocabulary such as emoticons, and newly coined words. Previous methods used only formal vocabulary to classify sentiments of sentences. However, these methods are not quite effective because internet users use sentences that contain informal vocabulary. In addition, we construct suggest to construct domain sentiment vocabulary because the same word may represent different sentiments in different domains. Feature vectors are extracted from the sentiment vocabulary information and classified by Support Vector Machine(SVM). Our proposed method shows good performance in classification accuracy.

• Journal of Convergence for Information Technology
• /
• v.10 no.10
• /
• pp.40-46
• /
• 2020

With the development of the Internet, users share their experiences and opinions. Since related keywords are used witho0ut considering information such as the general emotion or genre of an unstructured document such as a movie review, the sensitivity accuracy according to the appropriate emotional situation is impaired. Therefore, we propose a system that predicts emotions based on information such as the genre to which the unstructured document created by users belongs or overall emotions. First, representative keyword related to emotion sets such as Joy, Anger, Fear, and Sadness are extracted from the unstructured document, and the normalized weights of the emotional feature words and information of the unstructured document are trained in a system that combines CNN and LSTM as a training set. Finally, by testing the refined words extracted through movie information, morpheme analyzer and n-gram, emoticons, and emojis, it was shown that the accuracy of emotion prediction using emotions and F-measure were improved. The proposed prediction system can predict sentiment appropriately according to the situation by avoiding the error of judging negative due to the use of sad words in sad movies and scary words in horror movies.

• 한국HCI학회:학술대회논문집
• /
• 2008.02b
• /
• pp.411-416
• /
• 2008

The development of games has brought about the birth of game characters that are visually very realistic. At present, one sees much enthusiasm for giving the characters emotions through such devices as avatars and emoticons. However, in a freely changing environment of games, the devices merely allow for the expression of the value derived from a first input rather than creating expressions of emotion that actively respond to their surroundings. As such, there are as of yet no displays of deep emotions among game characters. In light of this, the present article proposes the 'CROSS(Character Reaction on Specific Situation) Model AE Engine' for game characters in order to develop characters that will actively express action and emotion within the environment of the changing face of games. This is accomplished by classifying the emotional components applicable to game characters based on the OCC model, which is one of the most well known cognitive psychological models. Then, the situation of game playing analysis of the commercialized RPG game is systematized by ontology.

• The Journal of the Korea Contents Association
• /
• v.12 no.12
• /
• pp.471-478
• /
• 2012

Various studies on sentiment classification of documents have been performed. Recently, they have been applied to twitter sentiment classification. However, they did not show good performances because they did not consider the characteristics of tweets such as tweet structure, emoticons, spelling errors, and newly-coined words. In this paper, we perform experiments on various input features (emoticon polarity, retweet polarity, author polarity, and replacement words) which affect twitter sentiment classification model based on machine-learning techniques. In the experiments with a sentiment classification model based on a support vector machine, we found that the emoticon polarity features and the author polarity features can contribute to improve the performance of a twitter sentiment classification model. Then, we found that the retweet polarity features and the replacement words features do not affect the performance of a twitter sentiment classification model contrary to our expectations.

• Journal of Korea Society of Industrial Information Systems
• /
• v.21 no.3
• /
• pp.35-46
• /
• 2016

Social network services (SNS) that help to build relationship network and share a particular interest or activity freely according to their interests by posting comments, photos, videos,${\ldots}$ on online communities such as blogs have adopted and developed widely as a social phenomenon. Several researches have been done to explore the pattern and valuable information in social networks data via text mining such as opinion mining and semantic analysis. For improving the efficiency of text mining, keyword-based approach have been applied but most of researchers argued the limitations of the rules of Korean orthography. This research aims to construct a database of non-standard Korean words which are difficulty in data mining such abbreviations, slangs, strange expressions, emoticons in order to improve the limitations in keyword-based text mining techniques. Based on the study of subjective opinions about specific topics on blogs, this research extracted non-standard words that were found useful in text mining process.

• Journal of Dental Anesthesia and Pain Medicine
• /
• v.19 no.4
• /
• pp.227-233
• /
• 2019

Background: Dental anxiety in children is a major barrier in patient management. If dental anxiety in pediatric patients is assessed during the first visit, it will not only aid in management but also help to identify patients who are in need of special care to deal with their fear. Nowadays, children and adults are highly interested in multimedia and are closely associated with them. Children usually prefer motion pictures on electronic devices than still cartoons on paper. Therefore, this study was conducted to evaluate a newly designed scale, the animated emoji scale (AES), which uses motion emoticons/animojis to assess dental anxiety in children during their first dental visit, and compare it with the Venham picture test (VPT) and facial image scale (FIS). Methods: The study included 102 healthy children aged 4-14 years, whose dental anxiety was measured using AES, VPT, and FIS during their first dental visit, and their scale preference was recorded. Results: The mean anxiety scores measured using AES, FIS, and VPT, represented as $mean{\pm}SD$, were $1.78{\pm}1.19$, $1.93{\pm}1.23$, and $1.51{\pm}1.84$, respectively. There was significant difference in the mean anxiety scores between the three scales (Friedman test, P < 0.001). The Pearson's correlation test showed a very strong correlation (0.73) between AES and VPT, and a strong correlation between AES and FIS (0.88), and FIS and VPT (0.69), indicating good validity of AES. Maximum number of children (74.5%) preferred AES. Conclusion: The findings of this study suggest that the AES is a novel and child-friendly tool for assessing dental anxiety in children.

• The Journal of the Korea Contents Association
• /
• v.21 no.1
• /
• pp.1-11
• /
• 2021

The users of a chatbot messenger can be better engaged in the conversation if they feel intimacy with the chatbot. This can be achieved by the chatbot's effective expressions of human emotions to chatbot users. Thus motivated, this study aims to identify the appropriate emotional expressions of a chatbot that make people feel the social presence of the chatbot. In the background research, we obtained that facial expression is the most effective way of emotions and movement is important for relationship emersion. In a survey, we prepared moving text, moving gestures, and still emoticon that represent five emotions such as happiness, sadness, surprise, fear, and anger. Then, we asked the best way for them to feel social presence with a chatbot in each emotion. We found that, for an arousal and pleasant emotion such as 'happiness', people prefer moving gesture and text most while for unpleasant emotions such as 'sadness' and 'anger', people prefer emoticons. Lastly, for the neutral emotions such as 'surprise' and 'fear', people tend to select moving text that delivers clear meaning. We expect that this results of the study are useful for developing emotional chatbots that enable more effective conversations with users.

• Management & Information Systems Review
• /
• v.38 no.4
• /
• pp.1-24
• /
• 2019

This study confirms the responses of consumers when the composition of emoticon bundles can be selected by individuals in MIM service. This aims to verify that customized bundling is a valid marketing strategy in the MIM emoticon market. Currently, the emoticon bundling used in Korean MIM services is in the form of pure bundling. As a result, Consumers must purchase an entire bundle even though he/she doesn't need to use all the emoticons contained in it. Some researches(e.g. Hitt & Chen, 2005; Wu & Anandalingam, 2002) show that when consumers value only part of the products or services included in pure bundling, customized bundling is much more profitable. In their works, customized bundling is appropriate when marginal costs are near zero. Information goods, such as emoticons, meet the condition. On the other hand, customized bundling increase the choosable options, so it can pose a problem of complexity (Blecker et al., 2004). And consumers may experience information overload(Huffman & Kahn, 1998). Thus, judgement on the necessity to introduce customized bundling needs to be made through empirical analyses in the light of characteristics of the product and the reaction of consumers. Results show that when customized bundling was introduced, consumers' purchase intention and willingness to pay significantly increased. Purchase intention for customized bundles has increased by 0.44 based on the five point Likert scale than the purchase intention for existing pure bundles. The increase in purchase intention for customized bundles was statistically independent of the existing purchasing experience. In addition, the willingness to pay was increased by about 2.8% compared to the price of the existing emoticon bundles in the whole group. The group with experience in purchasing pure bundles were willing to pay 5.9% more than pure bundles. The other group without experience in purchasing pure bundles were willing to buy if they were about 5% cheaper than the existing price. Overall, introducing customized bundling into emoticon bundles can lead to positive consumers responses and be a viable marketing strategy.

• Science of Emotion and Sensibility
• /
• v.24 no.3
• /
• pp.3-16
• /
• 2021

Studies have found that people with higher social status pay little attention to other people's emotions and facial expressions. However, only a few studies have made similar observations on adolescents with high cyberspace social status. Therefore, this study sought to identify how adolescents with different online game character social statuses interpreted the smile emoticons in negative and positive situations, that is, did they perceive the emoticon to be positive (smile, encouragement, and consolation) or negative (derision, ridicule, and sarcasm). In Experiment 1, the participants were separated into three groups; those who had a lower than global average online game character status, those who had the same as the global average, and those who had higher than the global average. The participants were then asked to judge the meaning of the smile emoticon received in various positive or negative situations. In Experiment 2, the game character levels of the participants were set to be either higher or lower than the others' characters, and they were again asked to judge the meaning of the smile emoticon received in the positive or negative situations. In Experiment 3, the participants were separated into four groups; lower level than the average game character status (no information on the level of acquaintance's game character), lower than the average but higher than the character of the other, higher than the average status (no information on the other's character level), and higher than the average but lower than the character of the other, and asked to judge the meaning of the smile emoticon in positive or negative situations. It was found that when participants had a lower-level character compared to the average, had a lower-level character than the other, and had higher than the average but lower than the other's character, they interpreted the smile emoticon as derision, ridicule, or sarcasm. However, participants with higher level characters, higher than that of the other, and lower than the average but higher than the other interpreted the emoticon as a smile or consolation. This study was significant because it demonstrated the impact of an adolescent's social cyberspace status on their online communication.

• Journal of the Korea Convergence Society
• /
• v.9 no.1
• /
• pp.419-431
• /
• 2018

In this paper, we propose a novel method for monitoring mood trend of Twitter users by analyzing their daily tweets for a long period. Then, to more accurately understand their tweets, we analyze all types of content in tweets, i.e., texts and emoticons, and images, thus develop a multimodal sentiment analysis method. In the proposed method, two single-modal analyses first are performed to extract the users' moods hidden in texts and images: a lexicon-based and learning-based text classifier and a learning-based image classifier. Thereafter, the extracted moods from the respective analyses are combined into a tweet mood and aggregated a daily mood. As a result, the proposed method generates a user daily mood flow graph, which allows us for monitoring the mood trend of users more intuitively. For evaluation, we perform two sets of experiment. First, we collect the data sets of 40,447 data. We evaluate our method via comparing the state-of-the-art techniques. In our experiments, we demonstrate that the proposed multimodal analysis method outperforms other baselines and our own methods using text-based tweets or images only. Furthermore, to evaluate the potential of the proposed method in monitoring users' mood trend, we tested the proposed method with 40 depressive users and 40 normal users. It proves that the proposed method can be effectively used in finding depressed users.