• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.85-109
• /
• 2018

Recommender system recommends the items expected to be purchased by a customer in the future according to his or her previous purchase behaviors. It has been served as a tool for realizing one-to-one personalization for an e-commerce service company. Traditional recommender systems, especially the recommender systems based on collaborative filtering (CF), which is the most popular recommendation algorithm in both academy and industry, are designed to generate the items list for recommendation by using 'overall rating' - a single criterion. However, it has critical limitations in understanding the customers' preferences in detail. Recently, to mitigate these limitations, some leading e-commerce companies have begun to get feedback from their customers in a form of 'multicritera ratings'. Multicriteria ratings enable the companies to understand their customers' preferences from the multidimensional viewpoints. Moreover, it is easy to handle and analyze the multidimensional ratings because they are quantitative. But, the recommendation using multicritera ratings also has limitation that it may omit detail information on a user's preference because it only considers three-to-five predetermined criteria in most cases. Under this background, this study proposes a novel hybrid recommendation system, which selectively uses the results from 'traditional CF' and 'CF using multicriteria ratings'. Our proposed system is based on the premise that some people have holistic preference scheme, whereas others have composite preference scheme. Thus, our system is designed to use traditional CF using overall rating for the users with holistic preference, and to use CF using multicriteria ratings for the users with composite preference. To validate the usefulness of the proposed system, we applied it to a real-world dataset regarding the recommendation for POI (point-of-interests). Providing personalized POI recommendation is getting more attentions as the popularity of the location-based services such as Yelp and Foursquare increases. The dataset was collected from university students via a Web-based online survey system. Using the survey system, we collected the overall ratings as well as the ratings for each criterion for 48 POIs that are located near K university in Seoul, South Korea. The criteria include 'food or taste', 'price' and 'service or mood'. As a result, we obtain 2,878 valid ratings from 112 users. Among 48 items, 38 items (80%) are used as training dataset, and the remaining 10 items (20%) are used as validation dataset. To examine the effectiveness of the proposed system (i.e. hybrid selective model), we compared its performance to the performances of two comparison models - the traditional CF and the CF with multicriteria ratings. The performances of recommender systems were evaluated by using two metrics - average MAE(mean absolute error) and precision-in-top-N. Precision-in-top-N represents the percentage of truly high overall ratings among those that the model predicted would be the N most relevant items for each user. The experimental system was developed using Microsoft Visual Basic for Applications (VBA). The experimental results showed that our proposed system (avg. MAE = 0.584) outperformed traditional CF (avg. MAE = 0.591) as well as multicriteria CF (avg. AVE = 0.608). We also found that multicriteria CF showed worse performance compared to traditional CF in our data set, which is contradictory to the results in the most previous studies. This result supports the premise of our study that people have two different types of preference schemes - holistic and composite. Besides MAE, the proposed system outperformed all the comparison models in precision-in-top-3, precision-in-top-5, and precision-in-top-7. The results from the paired samples t-test presented that our proposed system outperformed traditional CF with 10% statistical significance level, and multicriteria CF with 1% statistical significance level from the perspective of average MAE. The proposed system sheds light on how to understand and utilize user's preference schemes in recommender systems domain.

• Anxiety and mood
• /
• v.12 no.2
• /
• pp.103-112
• /
• 2016

Objective : This study was conducted to examine the reliability and validity of the Measure of Constructs Underlying Perfectionism-Korean version (M-CUP-K). Methods : Two hundred and six normal subjects completed a battery of measures including M-CUP-K, Frost Multidimensional Perfectionism Scale-Korean version (FMPS-K), and Beck Depression Inventory (BDI). Psychometric properties of the M-CUP-K were analyzed. Results : The principal component analysis for construct validity resulted in 56 items composed of 6 factors (factor 1 : Dissatisfaction-Reactivity to Mistakes; factor 2 : Order-Details and Checking ; factor 3 : Satisfaction ; factor 4 : High standards ; factor 5 : Perceived Pressure from Others-Perfectionism toward Others ; factor 6 : Black and White Thinking about Tasks and Activities), compared to the original version. The M-CUP-K total and subscale scores were more strongly correlated with those of the other perfectionism-specific measure, FMPS-K, with a correlation of 0.822 (convergent validity) than with those of the nonspecific depression measure (discriminant validity). The Cronbach's ${\alpha}$ value for internal consistency of M-CUP-K was in an excellent range (r=0.872-0.935). The test-retest reliability for external validity suggested a good temporal stability with a total score correlation of 0.827. Conclusion : This study revealed that the M-CUP-K has good reliability and validity. Therefore, the M-CUP-K can be used as a promising measure of perfectionism in Korea.

• Anxiety and mood
• /
• v.13 no.2
• /
• pp.66-73
• /
• 2017

Objective : The purpose of this study was to examine the effects of adjunctive aripiprazole versus bupropion on specific symptoms of depression. Methods : Data were from 6-week, randomized, prospective, open-label multi-center study in 103 patients with major depressive disorders. Participants were randomized to receive aripiprazole (2.5-10 mg/day) or bupropion (150-300 mg/day) for 6 weeks. Change in four subscales of the 17-item Hamilton Depression Rating Scale (HAM-D17) that capture core depression symptoms was determined, and change in individual HAM-D17 items was also assessed. Changes in three composite subscales-anxiety, insomnia, and drive were also examined. Results : Within-group change in the four core subscales was large [effect size (ES)=1.30-1.47] and it was similar to that in the HAM-D17 total score. Differences between aripiprazole and bupropion were significant for each of the four core subscales and the HAM-D17 total score favored aripiprazole (p<0.001). On three composite scales, both treatments caused substantial changes in anxiety (within-group ES=1.10 (aripiprazole) vs. 1.00 (bupropion)], insomnia (ES=0.75 vs 0.50), and drive (ES=1.17 vs 1.15). Conclusion : This results suggested that both aripiprazole and bupropion adjunctive therapies with selective serotonin reuptake inhibitors resulted in significant and clinically meaningful changes in core symptom subscales for depression.

• Korean Journal of Psychosomatic Medicine
• /
• v.22 no.2
• /
• pp.112-120
• /
• 2014

Objectives : The aim of this study is to evaluate the clinical characteristics of night eating syndrome(NES) in bipolar disorder outpatients. Methods : The 14 items of self-reported night eating questionnaire(NEQ) was administered to 84 bipolar patients in psychiatric outpatient clinic. We examined demographic and clinical characteristics, body mass index(BMI), subjective measures of mood, sleep, binge eating & weight-related quality of life using Beck's Depression Inventory (BDI), Pittsburgh Sleep Quality Index(PSQI), Binge Eating Scale(BES) and Korean version of Obesity-Related Quality of Life Scale(KOQoL), respectively. Results : The prevalence of night eating syndrome in bipolar outpatients was 14.3%(12 of 84). Comparisons between NES group and non-NES group revealed no significant differences in demographic characteristics, BMI and clinical status except economic status and comorbid medical illnesses. However, compared to non-NES, patients with NES was more likely to have binge eating pattern and poorer weight-related quality of life. Conclusions : This study is to be the first to describe the clinical correlates of night eaters in bipolar outpatients. Although there were few significant correlates of NES in bipolar outpatients, relatively high prevalence of NES suggest that clinicians should be aware to assess the patients with bipolar disorder on NES, regardless of obesity status of patients.

• Journal of Yeungnam Medical Science
• /
• v.7 no.2
• /
• pp.79-87
• /
• 1990

Using Zung's self-rating depression scale, the authors studied depression in 310 elderlies residing in the 9 home for the aged (HFA) in Kyungbuk area, and 234 elderlies living in Taegu city and 107 elderlies attending a Life-long education program in Taegu, which serve as a control group, Community resident elderlies(CRE). The research had been administered during the period from June to August, 1986. The results were as follows : 1. The mean scores of male. female. and the total of the elderlies in HFA were $38.95{\pm}11.55$, $44.18{\pm}14.15$:: and $42.8{\pm}13.7$ respectively while CRE marked $40.8{\pm}11.3$ for male, $45.2{\pm}12.0$ for female, and $43.4{\pm}11.9$ for the total. Therefore there were significant differences between male and female in both groups(p<0.01, p<0.001), though no significant difference between the two groups. However, the depression score of elderlies in HFA might be much higher than that of CRE if 81 elderlies(14.2%) in HFA who had been left out of the statistical evaluation due to their having severe depression, organic brain syndrom, or pseudoementia, etc had been included. 2. The score distribution by items for the elderlies in HFA were from highest scores hopelessness, worthlessness, emptiness, decreased appetite, confusion, while for CRE, hopelessness, decreased appetite, psychomotor retardation, indecisiveness, and worthlessness. Elderlies in HFA showed significantly high scores in depressed mood, weight loss, suicidal rumination(ideation) and psychomotor excitement, while CRE showed significantly high scores in decreased appetite, psychomotor retardation, indecisiveness, and dissatisfaction. 3. Elderlies who scored over 50 numbered 10 males(16%), 57 females(34%), and total of 67(29%) in HFA and 28 males(21%), 77 females(37%), and total of 105(31%) in CRE : female showed higher seores in both groups. 4. Psychosocial factors such as getting older(respectively p<0.01, p<0.01), being Buddhist(respectively p<0.01, p<0.01), and monthly pocket money less than \30,000(respectively p<0.001, p<0.001) were found to have a noticable impact on the depression level of the elderlies in both groups. Factors such as illiteracy (p<0.001, monthly pocket money less than \10,000(p<0.05), and having no family(p<0.01) recorded significantly higher scores among CRE than the elderlies in HFA.

• Korean Journal of Psychosomatic Medicine
• /
• v.3 no.2
• /
• pp.115-125
• /
• 1995

Reports about the prevalence of premenstrual symptoms state that occurs in 20 to 100% of most reproductive-age women. There is a close association between premenstrual syndrome and affective disorders as well as same some other psychiatric disorders. Late luteal phase dysphoric disorder (LLPDD) is a premenstrual condition defined in DSM-III-R by severe mood changes and other symptoms that repeatedly occur only in the luteal phase of the menstrual cycle. However, DSM-III-R does not specify how to compute the change from the follicular to the luteal phase or how to determine when the amount of change is great enough to warrant the diagnosis nor how to determine occupational or social functional impairment. This study was conducted to evaluate the nature, severity and magnitude of premenstrual syndrome in women with current psychiatric disorders by using prospective Daily Rating Form(DRF), and to measure symptom changes according to three scoring methods for diagnosing LLPDD. Our study obtains the data about premenstrual changes estimated by DRF from 22 women with psychiatric disorders who had met criteria for major depressive syndrome on the Premenstrual Assessment Form (PAF). The data was scored by each three methods and was determined to meet criteria A for LLPDD. The results are as follows: 1) the subjects, when scored according to the percent change method, effect size method and absolute severity method, met the DSM-III-R criteria A for LLPDD in 36.4% (8 subjects), 14% (3 subjects) and 4.5% (1 subject) of the cases respectively. 2) The items of irritability, anger and impatience were occurred most frequently on the DRF, when it was scored according to the three scoring methods. And the item of breast pain was next frequent according to the effect size method and the percent change method but according to the absolute severity method. 3) The PAF item of impaired social functioning was reported by 16 (73%) of the subjects. 4) 4 (18%) of the subjects met criteria A for LLPDD and reported impaired social functioning. The prevalency of LLPDD according to each method varied. The percent change method yielded the greatest (36.4%), and the absolute seventy method yielded the laest (4.5%), The effect size method yielded an intermediate frequency (14%). Therefore, for maximizing the diagnostic accuracy of LLPDD, a diagnostic procedure including a measure of change (e.q., effect size method, percent change method) as well as confirmed diagnosis by DRF, will be needed. Also, an accurate tool to evaluate impaired social functioning will be required.

• Anxiety and mood
• /
• v.4 no.1
• /
• pp.34-41
• /
• 2008

Objective : The aim of this study is to examine the characteristics of somatic symptoms in patients with PTSD according to trauma type. Methods : The subjects of this study were 84 patients diagnosed with PTSD according to the DSM-IVTR and CAPS criteria. The subjects ranged in age from 18 to 76 years, and they were recruited from 18 hospitals across the nation. All participants were asked about their trauma history, and they all completed the Davidson Trauma Scale (DTS), Beck Depression Inventory (BDI), State-Trait Anxiety Inventory (STAI), Impact of Event Scale-Revised (IES-R) and Korean-Physical Somatic Symptom Inventory (K-PSI). The items of the K-PSI were categorized into 5 groups according to organ system, and the participants were classified into 6 groups according to trauma type. We compared the results of the social demographical scale, DTS, BDI, STAI, IES-R and each recategorized subscale of the K-PSI among the six groups. Results : There were significant differences between the 6 groups in terms of the Korean-Physical Somatic Symptom Inventory scores for each organ system, except for the cardiopulmonary system, as well as the BDI scores. Post hoc analysis revealed differences between the combat-related trauma group and all other groups but not among any of the other groups. Conclusion : Our result showed that there were significant differences in the somatic symptom scores among the 6 trauma groups. However, patient age and the time elapsed since the traumatic event may have hada crucial influence on the result of this study.

• Anxiety and mood
• /
• v.4 no.1
• /
• pp.49-54
• /
• 2008

Objective : This article is a part of the Korean Medication Algorithm Project for Panic Disorder, which aims to build consensus regarding the diagnosis, treatment response and achievement of clinical remission for patients with panic disorder in Korea. Methods : The questionnaire used in this article had parts : 1) diagnosis, 2) treatment response, and 3) remission for patients with panic disorder. The questionnaire was completed by each of 54 Korean psychiatrists who had much experience in treating patients with panic disorder. We classified the experts' opinions into 3 categories (first-line, second-line, and third-line) using the ${\chi}^2$-test. Results : Five factors were considered in this research : panic attack, anticipatory anxiety, phobic avoidance, severity of illness, and psychosocial disability. Most reviewers agreed that the presence of a panic attack was the most important factor in the diagnosis of patients with panic disorder. Phobic avoidance was included in the first-line category, whereas the severity of illness and psychosocial disability were included in the second-line category. Most reviewers also agreed that the presence of a panic attack was the most important factor in determining the appropriate treatment response, and it was included in the first-line category along with several other items. To determine remission status, the patients' scores on tests pertaining to the severity of panic attack, anticipatory anxiety, phobic avoidance, severity of illness and psychosocial disability should be less than 3.0-3.3 on a 9-point Likert scale. Conclusion : We suggest useful information for making a diagnosisof panic disorder, determining the appropriate treatment response and identifying remission in panic disorder patients on the basis of the results of a nationwide survey of experts in Korea.

• Clinical Psychopharmacology and Neuroscience
• /
• v.16 no.4
• /
• pp.434-448
• /
• 2018

Objective: The Korean Medication Algorithm Project for Bipolar Disorder (KMAP-BP) was first published in 2002 through an expert consensus of opinion, and updated in 2006, 2010, and 2014. This study constitutes the fourth revision of the KMAP-BP. Methods: A 50-item questionnaire was used to obtain the consensus of experts regarding pharmacological treatment strategies for various phases of adult bipolar disorder and six items for pediatric bipolar disorder. The review committee included 84 Korean psychiatrists and 43 child and adolescent psychiatry experts. Results: The preferred first-step strategies for acute mania were the combination of a mood stabilizer (MS) and an atypical antipsychotic (AAP), MS monotherapy, and AAP monotherapy. A combination of a MS and an AAP, and AAP monotherapy were preferred for psychotic mania. The first-step strategies for mild to moderate bipolar depression were monotherapy with MS, AAP, or lamotrigine (LMT), and the combination of a MS and an AAP or LMT, or a combination of an AAP and LMT. The combination of two among a MS, AAP, and LMT were preferred for non-psychotic severe depression. A combination of a MS and an AAP or the combination of an AAP with an antidepressant or LMT were the first-line options for psychotic severe depression. Conclusion: The recommendations of the KMAP-BP 2018 have changed from the previous version by reflecting recent developments in pharmacotherapy for bipolar disorder. KMAP-BP 2018 provides clinicians with a wealth of information regarding appropriate strategies for treating patients with bipolar disorder.

• Anxiety and mood
• /
• v.15 no.1
• /
• pp.53-60
• /
• 2019

Objective : GRIT is a non-cognitive trait which is defined as perseverance and passion for long-term goals. It predicts success, performance and thedifference from other traits. The purpose of this study was to examine the reliability and validity of the Korean version of the GRIT scale. Methods : A total of 92 patients were enrolled in the study. All patients received psychiatric assessment including Clinical Useful Depression Outcome Scale (CUDOS), Clinical Useful Anxiety Outcome Scale (CUXOS), Patient Health Questionnaire (PHQ-15), Connor-Davidson Resilience Scale (CDRS), Brief Resilience Scale (BRS), and GRIT as well as demographic assessment. Cronbach's alpha coefficient of total GRIT score and the split-half reliability of each item was calculated to assess test reliability. Exploratory and confirmatory factor analyses were performed to select the best fitting model and assess construct validity. Finally, a correlation analysis was performed to check convergent and discriminant validity. Results : Cronbach's alpha coefficient for GRIT was found to be 0.85 and all Cronbach's alpha were more than 0.8 even in cases where all items were deleted. We found 3 appropriate factor models in exploratory factor analysis, compared them with 3 models and chose the 2-factor model as the most suitable based on the best fit test. Finally, correlation of the GRIT with CUDOS, CUXOS, PHQ-15, CDRS and BRS were statistically significant (all p<0.01), with relatively low correlation coefficient. Conclusion : This study indicates that the Korean version of GRIT is a reliable and valid instrument for investigating individual power of passion and perseverance.