• Dementia and Neurocognitive Disorders
• /
• v.23 no.3
• /
• pp.146-160
• /
• 2024

Background and Purpose: The emotions of people at various stages of dementia need to be effectively utilized for prevention, early intervention, and care planning. With technology available for understanding and addressing the emotional needs of people, this study aims to develop speech emotion recognition (SER) technology to classify emotions for people at high risk of dementia. Methods: Speech samples from people at high risk of dementia were categorized into distinct emotions via human auditory assessment, the outcomes of which were annotated for guided deep-learning method. The architecture incorporated convolutional neural network, long short-term memory, attention layers, and Wav2Vec2, a novel feature extractor to develop automated speech-emotion recognition. Results: Twenty-seven kinds of Emotions were found in the speech of the participants. These emotions were grouped into 6 detailed emotions: happiness, interest, sadness, frustration, anger, and neutrality, and further into 3 basic emotions: positive, negative, and neutral. To improve algorithmic performance, multiple learning approaches were applied using different data sources-voice and text-and varying the number of emotions. Ultimately, a 2-stage algorithm-initial text-based classification followed by voice-based analysis-achieved the highest accuracy, reaching 70%. Conclusions: The diverse emotions identified in this study were attributed to the characteristics of the participants and the method of data collection. The speech of people at high risk of dementia to companion robots also explains the relatively low performance of the SER algorithm. Accordingly, this study suggests the systematic and comprehensive construction of a dataset from people with dementia.

• Journal of Digital Convergence
• /
• v.16 no.7
• /
• pp.97-105
• /
• 2018

The fourth industrial revolution is expected to bring about great changes in information technology sector and create a variety of jobs. However, the psychological anxiety of IT staff is increasing due to stress and uncertainty created by the new technologies. Accordingly, researchers examined how professional identity moderate the effect of job stress of system maintenance staff on emotion exhaustion. For empirical studies, data was collected from 160 employees responsible for managing and supporting IS, and the hypothesis was verified using SPSS 21. The analysis results showed that role conflicts, role ambiguity, and qualitative work overload, which are components of job stress, have affected the emotion exhaustion. Professional identity had a moderating effect the relationship between qualitative work overload and emotion exhaustion. On the other hand, professional identity did not moderate the relationship between role conflict and emotion exhaustion, role ambiguity and emotion exhaustion. As professional identity lessen the psychological burden and emotion exhaustion of introducing new technologies, organizations need to provide support to enhance professional identity for system maintenance staff.

• Journal of Digital Convergence
• /
• v.17 no.3
• /
• pp.107-117
• /
• 2019

In the era of SNS, many people relies on it to express their emotions about various kinds of products and services. Therefore, for the companies eagerly seeking to investigate how their products and services are perceived in the market, emotion mining tasks using dataset from SNSs become important much more than ever. Basically, emotion mining is a branch of sentiment analysis which is based on BOW (bag-of-words) and TF-IDF. However, there are few studies on the emotion mining which adopt feature selection (FS) methods to look for optimal set of features ensuring better results. In this sense, this study aims to propose FS methods to conduct emotion mining tasks more effectively with better outcomes. This study uses Twitter and SemEval2007 dataset for the sake of emotion mining experiments. We applied three FS methods such as CFS (Correlation based FS), IG (Information Gain), and ReliefF. Emotion mining results were obtained from applying the selected features to nine classifiers. When applying DT (decision tree) to Tweet dataset, accuracy increases with CFS, IG, and ReliefF methods. When applying LR (logistic regression) to SemEval2007 dataset, accuracy increases with ReliefF method.

• Smart Media Journal
• /
• v.13 no.10
• /
• pp.19-27
• /
• 2024

Recently, as the demand for non-face-to-face counseling has rapidly increased, the need for emotion recognition technology that combines various aspects such as text, voice, and facial expressions is being emphasized. In this paper, we address issues such as the dominance of non-Korean data and the imbalance of emotion labels in existing datasets like FER-2013, CK+, and AFEW by using Korean video data. We propose methods to enhance multimodal emotion recognition performance in videos by integrating the strengths of image modality with text modality. A pre-trained model is used to overcome the limitations caused by small training data. A GPT-4-based LLM model is applied to text, and a pre-trained model based on VGG-19 architecture is fine-tuned to facial expression images. The method of extracting representative emotions by combining the emotional results of each aspect extracted using a pre-trained model is as follows. Emotion information extracted from text was combined with facial expression changes in a video. If there was a sentiment mismatch between the text and the image, we applied a threshold that prioritized the text-based sentiment if it was deemed trustworthy. Additionally, as a result of adjusting representative emotions using emotion distribution information for each frame, performance was improved by 19% based on F1-Score compared to the existing method that used average emotion values for each frame.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2000.04a
• /
• pp.173-178
• /
• 2000

Subjective correspondence among visual variables, auditory variables and vibratory feedback to a hand was experimentally examined to improve usability of a remote controller. First, we studied the correspondence among visual variables represented on a screen or auditory variables and the duration of vibratory stimulus to the subjects' hand by subjective evaluation. Subjective rating method was used in ten items; suitability, comprehensibility, ease-to-use, naturalness, variety, activity, usualness, interest, wish-to-use and feeling of pleasure. Second, to show the effects of multi-modal interface using visual sense, the sense of auditory and vibratory sense, we combined positive stereotype of visual variables and auditory variables provided with the first experiment. The results showed some stereotype between visual variables or auditory variables and duration of vibratory stimulus. Some of the variables such as size, direction of motion, hue, brightness of color and volume of sound had high correspondence with the duration of vibration.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2000.04a
• /
• pp.230-234
• /
• 2000

Thermal comfort by wearing clothes is the important element which gives influence to a clothing comfort. The thermal comfort of clothes have been evaluated by sensory test and physical property of clothes material. To evaluate a thermophysiological comfort. a new evaluation method which measures the physiological response such as electroencephalogram(EEG) is attracting the attention of many people. In the chilly environment, the EEGs in t재 kinds of thermal conditions : with and without clothes were measured. By utilizing the chaos analysis, the behavior of the obtained EEGs were quantiatively expressed in the correlation dimension. As a result, the correlation dimension of the EEGs in being thermal comfortable feeling by putting on clothes, was bigger than the correlation dimension of the EEGs in being cold and discomfort. These results suggest that chaotic analysis of EEG is effective to the quantitative evaluation of thermal esthesis.

• Journal of Information Technology Applications and Management
• /
• v.21 no.4
• /
• pp.203-223
• /
• 2014

This study proposes a novel context-aware recommender system, which is designed to recommend the items according to the customer's responses to the previously recommended item. In specific, our proposed system predicts the user's emotional state from his or her responses (such as facial expressions and movements) to the previous recommended item, and then it recommends the items that are similar to the previous one when his or her emotional state is estimated as positive. If the customer's emotional state on the previously recommended item is regarded as negative, the system recommends the items that have characteristics opposite to the previous item. Our proposed system consists of two sub modules-(1) emotion prediction module, and (2) responsive recommendation module. Emotion prediction module contains the emotion prediction model that predicts a customer's arousal level-a physiological and psychological state of being awake or reactive to stimuli-using the customer's reaction data including facial expressions and body movements, which can be measured using Microsoft's Kinect Sensor. Responsive recommendation module generates a recommendation list by using the results from the first module-emotion prediction module. If a customer shows a high level of arousal on the previously recommended item, the module recommends the items that are most similar to the previous item. Otherwise, it recommends the items that are most dissimilar to the previous one. In order to validate the performance and usefulness of the proposed recommender system, we conducted empirical validation. In total, 30 undergraduate students participated in the experiment. We used 100 trailers of Korean movies that had been released from 2009 to 2012 as the items for recommendation. For the experiment, we manually constructed Korean movie trailer DB which contains the fields such as release date, genre, director, writer, and actors. In order to check if the recommendation using customers' responses outperforms the recommendation using their demographic information, we compared them. The performance of the recommendation was measured using two metrics-satisfaction and arousal levels. Experimental results showed that the recommendation using customers' responses (i.e. our proposed system) outperformed the recommendation using their demographic information with statistical significance.

• Science of Emotion and Sensibility
• /
• v.16 no.2
• /
• pp.157-166
• /
• 2013

There are few that evaluate tactile emotion as it pertains to car interior parts, while studies on visual evaluations of car interiors as well as usability tests in a visual sense are numerous. The purpose of this study is to determine typical in-vehicle tactile emotions so that they can be used to evaluate tactile impressions of car interior parts. 52 words related to tactile impressions of car interiors were gathered from a survey in conjunction with an in-vehicle test, interviews with the car salespersons, and an analysis of car reviews. After a factor analysis with 52 words, 10 categories of major tactile emotions were clustered. These were roughness, toughness, friction, comfortability, stiffness, softness, temperature, sleekness, familiarity, and flexibility. These representative tactile emotions regarding a car interior can be used to evaluate tactile impressions of surfaces such as leather, plastic, metal and wood when used as parts in car interiors.

• Nutrition Research and Practice
• /
• v.10 no.4
• /
• pp.456-463
• /
• 2016

BACKGROUND/OBJECTIVES: Setting healthful beverage expectations, making calcium-rich foods and beverages (CRF/B) available, and role modeling are parenting practices promoting calcium intake among early adolescents. This study aimed to evaluate emotion-based messages designed to motivate parents of early adolescents to perform these practices. SUBJECTS/METHODS: Emotion-based messages were developed for each parenting practice and tested in 35 parents from 5 states. Findings were used to modify messages and develop a survey administered via Amazon MechanicalTurk to a convenience sample of Asian (n = 166) and Hispanic (n = 184) parents of children 10-13 years. Main outcome measures were message comprehension, motivation, relevance, acceptability, and novelty. Engagement in the parenting practices was also assessed. RESULTS: Message comprehension was acceptable for the majority of parents. Most also agreed that messages were motivational (setting healthful beverage expectations (69.0%), making CRF/B available (67.4%), and role modeling (80.0%)), relevant and acceptable. About 30-50% indicated they had not seen the information before. Many parents indicated they were already engaging in the practices (> 70%). No racial/ethnic differences were observed for responses to messages or engaging in parenting practices. CONCLUSIONS: Results indicate that emotion-based messages designed to motivate parents to engage in parenting practices that promote calcium intake among early adolescents were motivating, relevant, and acceptable.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.3 s.303
• /
• pp.29-38
• /
• 2005

Although people frequently rely on intuition in managing activities, they rarely use it in developing effective decision-making support systems. In this paper, we investigate and compare the correlations between such characteristics as cognition and emotion characteristics and judgmental time-series forecasting accuracy by using a self-organizing neural network, and eventually aim to help build efficient decision-making atmosphere. The neural network used in this paper employs a self-supervised adaptive algorithm, and the feature of which is that it inherently can use correlation between input vectors by exchanging information between neuron clusters in the self-organizing layer during the training. Our experiments showed that both cognition and emotion characteristics had correlations with judgmental time-series forecasting, and that cognition characteristics had larger correlation than emotion characteristics. We also found that conceptual style had larger correlation than behavioral and analytical styles, and displeasure-sleepiness style had larger correlation than pleasure-arousal style with the forecasting.