• Title/Summary/Keyword: 소비자감정

Search Result 312, Processing Time 0.032 seconds

Development of Music Recommendation System based on Customer Sentiment Analysis (소비자 감성 분석 기반의 음악 추천 알고리즘 개발)

  • Lee, Seung Jun;Seo, Bong-Goon;Park, Do-Hyung
    • Journal of Intelligence and Information Systems
    • /
    • v.24 no.4
    • /
    • pp.197-217
    • /
    • 2018
  • Music is one of the most creative act that can express human sentiment with sound. Also, since music invoke people's sentiment to get empathized with it easily, it can either encourage or discourage people's sentiment with music what they are listening. Thus, sentiment is the primary factor when it comes to searching or recommending music to people. Regard to the music recommendation system, there are still lack of recommendation systems that are based on customer sentiment. An algorithm's that were used in previous music recommendation systems are mostly user based, for example, user's play history and playlists etc. Based on play history or playlists between multiple users, distance between music were calculated refer to basic information such as genre, singer, beat etc. It can filter out similar music to the users as a recommendation system. However those methodology have limitations like filter bubble. For example, if user listen to rock music only, it would be hard to get hip-hop or R&B music which have similar sentiment as a recommendation. In this study, we have focused on sentiment of music itself, and finally developed methodology of defining new index for music recommendation system. Concretely, we are proposing "SWEMS" index and using this index, we also extracted "Sentiment Pattern" for each music which was used for this research. Using this "SWEMS" index and "Sentiment Pattern", we expect that it can be used for a variety of purposes not only the music recommendation system but also as an algorithm which used for buildup predicting model etc. In this study, we had to develop the music recommendation system based on emotional adjectives which people generally feel when they listening to music. For that reason, it was necessary to collect a large amount of emotional adjectives as we can. Emotional adjectives were collected via previous study which is related to them. Also more emotional adjectives has collected via social metrics and qualitative interview. Finally, we could collect 134 individual adjectives. Through several steps, the collected adjectives were selected as the final 60 adjectives. Based on the final adjectives, music survey has taken as each item to evaluated the sentiment of a song. Surveys were taken by expert panels who like to listen to music. During the survey, all survey questions were based on emotional adjectives, no other information were collected. The music which evaluated from the previous step is divided into popular and unpopular songs, and the most relevant variables were derived from the popularity of music. The derived variables were reclassified through factor analysis and assigned a weight to the adjectives which belongs to the factor. We define the extracted factors as "SWEMS" index, which describes sentiment score of music in numeric value. In this study, we attempted to apply Case Based Reasoning method to implement an algorithm. Compare to other methodology, we used Case Based Reasoning because it shows similar problem solving method as what human do. Using "SWEMS" index of each music, an algorithm will be implemented based on the Euclidean distance to recommend a song similar to the emotion value which given by the factor for each music. Also, using "SWEMS" index, we can also draw "Sentiment Pattern" for each song. In this study, we found that the song which gives a similar emotion shows similar "Sentiment Pattern" each other. Through "Sentiment Pattern", we could also suggest a new group of music, which is different from the previous format of genre. This research would help people to quantify qualitative data. Also the algorithms can be used to quantify the content itself, which would help users to search the similar content more quickly.

The Cause-and-Effect Relationship between Perceptual Satisfaction and Expectation Factors for Special Hospitals by Busan and Gyungnam Medical Consumers (부산·경남지역 의료소비자들의 전문병원에 대한 지각 만족도와 기대요소 간의 인과관계)

  • Park, Ki-Hyeok;Shin, Jin-Ho
    • Journal of Convergence for Information Technology
    • /
    • v.11 no.7
    • /
    • pp.181-188
    • /
    • 2021
  • This study was performed to examine the strategy method for the sustainable stability and effectiveness of small and medium hospital, where the relationship between perceptual satisfaction and expectation factors for special hospital was analyzed. The structural questionnaire was given to the residents of Busan and Gyungnam over the age of 20 and the square contingency and the logistical regression were employed for the analysis of the results. First, the respondent with 68.0% has realized the hospital claiming to be characterization as the special hospital and the Ministry of Health and Welfare designated hospital was identified to the respondent of 21.3%. Second, perceptual satisfaction with expectation level was satisfied to the most visitor in case of visiting special hospitals with subjective perception and was confirmed to the intention of revisiting consistently. Third, for the perceptual satisfaction of visiting with expectation level, the safety and the quality of treatment affected significantly the cause-and-effect. The result has provided the useful information with the establishment of a strategy for the long-term and continued effect through the perceptual satisfaction and the emotional attachment.

A Study on the Mechanism of Social Robot Attitude Formation through Consumer Gaze Analysis: Focusing on the Robot's Face (소비자 시선 분석을 통한 소셜로봇 태도 형성 메커니즘 연구: 로봇의 얼굴을 중심으로)

  • Ha, Sangjip;Yi, Eunju;Yoo, In-jin;Park, Do-Hyung
    • Journal of Intelligence and Information Systems
    • /
    • v.28 no.1
    • /
    • pp.243-262
    • /
    • 2022
  • In this study, eye tracking was used for the appearance of the robot during the social robot design study. During the research, each part of the social robot was designated as AOI (Areas of Interests), and the user's attitude was measured through a design evaluation questionnaire to construct a design research model of the social robot. The data used in this study are Fixation, First Visit, Total Viewed, and Revisits as eye tracking indicators, and AOI (Areas of Interests) was designed with the face, eyes, lips, and body of the social robot. And as design evaluation questionnaire questions, consumer beliefs such as Face-highlighted, Human-like, and Expressive of social robots were collected and as a dependent variable was attitude toward robots. Through this, we tried to discover the mechanism that specifically forms the user's attitude toward the robot, and to discover specific insights that can be referenced when designing the robot.

The Prediction of the Helpfulness of Online Review Based on Review Content Using an Explainable Graph Neural Network (설명가능한 그래프 신경망을 활용한 리뷰 콘텐츠 기반의 유용성 예측모형)

  • Eunmi Kim;Yao Ziyan;Taeho Hong
    • Journal of Intelligence and Information Systems
    • /
    • v.29 no.4
    • /
    • pp.309-323
    • /
    • 2023
  • As the role of online reviews has become increasingly crucial, numerous studies have been conducted to utilize helpful reviews. Helpful reviews, perceived by customers, have been verified in various research studies to be influenced by factors such as ratings, review length, review content, and so on. The determination of a review's helpfulness is generally based on the number of 'helpful' votes from consumers, with more 'helpful' votes considered to have a more significant impact on consumers' purchasing decisions. However, recently written reviews that have not been exposed to many customers may have relatively few 'helpful' votes and may lack 'helpful' votes altogether due to a lack of participation. Therefore, rather than relying on the number of 'helpful' votes to assess the helpfulness of reviews, we aim to classify them based on review content. In addition, the text of the review emerges as the most influential factor in review helpfulness. This study employs text mining techniques, including topic modeling and sentiment analysis, to analyze the diverse impacts of content and emotions embedded in the review text. In this study, we propose a review helpfulness prediction model based on review content, utilizing movie reviews from IMDb, a global movie information site. We construct a review helpfulness prediction model by using an explainable Graph Neural Network (GNN), while addressing the interpretability limitations of the machine learning model. The explainable graph neural network is expected to provide more reliable information about helpful or non-helpful reviews as it can identify connections between reviews.

A Study on Consumption Emotion of the Appearance Management Behaviors in University Students (남녀대학생의 외모관리행동에 관한 소비감정 연구)

  • Lee, Je Sung;Lee, June Young
    • Fashion & Textile Research Journal
    • /
    • v.19 no.6
    • /
    • pp.712-722
    • /
    • 2017
  • Attention to appearance is a common concern for all. Images created by appearance play an important role in judging people in terms of social life in contemporary society. This study investigated general behaviours of appearance management behaviours of both male and female college students, and categorised consumption emotion experienced by appearance management. In this regards, it was examined how consumers' psychological mechanism of consumption emotions influences consumers' satisfaction and their behavioural intentions. The main results are as follows: First, female students invest more time and money into appearance management compare to male students and have a higher level of attention. Secondly, both male and female students experience a variety of consumption emotions in appearance management behaviours. According to gender, female students show a higher level of positive and negative consumption emotions than male students. Thirdly, there are five emotional types (Confidence, Annoyance, Refreshment, Enjoyment, Anxiety) as the result of the consumption emotional typology in terms of appearance management behaviours of male and female university students. Fourthly, there are different emotional groups which influence consumers' satisfaction or behavioural intention according to gender in appearance management behaviour. In general, emotional groups such as 'Confidence, Delight and Anxiety' have a positive influence on consumers' satisfaction and behavioral intention, and 'Annoyance' composed of negative emotions have negative influence. In this respect, this research can contribute to beauty product development and marketing strategy with reflecting consumption emotion, and better understanding of consumption culture of university students which plays a pivotal role in appearance management behavior.

Consumer Responses to Stockouts in Online Fashion Stores: Indicating Effects of Psychological Reactance and Emotion (온라인 패션점포의 품절에 대한 소비자 반응: 심리적 반발심과 감정의 매개효과를 중심으로)

  • Shin, Hyesun;Hur, Hee Jin;Choo, Ho Jung
    • Fashion & Textile Research Journal
    • /
    • v.17 no.5
    • /
    • pp.770-780
    • /
    • 2015
  • This study intended to explore fundamental causes affecting consumers' response actions from psychological factors in the situation of sellout occurring during shopping in online fashion stores. In addition, this study devised a virtual online shop in order to measure consumers' cognitive and emotional psychological responses they experienced when goods were sold out. The subjects involved women in 20s~30s, major customers of online shopping, and the subjects were randomly allocated to one of eight questionnaire forms (2(stockout size: high vs low)${\times}2$(product assortment similarity: similar vs. dissimilar)${\times}2$(restocking cue: included vs excluded)). The number of final data used for the analysis was 336 and through SPSS 21.0 program, two-way ANOVA and bootstrap were utilized. The analysis result was that consumers' psychological responses (emotions, psychological reactance) of online shops differed by means of varying stockout situations. The stockout size had positive effect on psychological reactance and negative emotions. On the other hand, there was no difference in positive emotions (arousal) according to stockout size. In stockout situation of online fashion store, the moderating effect of product assortment similarity and restocking cues were verified. According to the analysis result, interaction effects between stockout size and restocking cues, product stockout size and product assortment for psychological reactance were significant. Lastly, the mediation effect of psychological reactance and emotion between stockout size and behavioral response was tested. As a result, the moderated mediation effects of psychological reactance for substitute were significant when product assortment was dissimilar and restocking cue was exclude.

Effects of Brand Knowledge and Affect on Brand Choice Confidence of Global Fashion Brands -Moderation Effect of Overseas Residence Experience- (브랜드 지식과 감정이 글로벌 패션 브랜드 선택 확신에 미치는 영향 -해외 거주 경험의 조절 효과-)

  • Kim, Su-Young;Lee, Yu-Ri;Choo, Ho-Jung
    • Journal of the Korean Society of Clothing and Textiles
    • /
    • v.36 no.8
    • /
    • pp.837-848
    • /
    • 2012
  • This study examines how the overseas residence experience of Korean consumers influences the relationship of global fashion brand knowledge and brand choice confidence. We contrast two kinds of consumer brand knowledge, using the concepts of Alba and Hutchinson's expertise and familiarity. Considering the effect of positive affect on intuitive information processing, the present study investigated the role of positive affect in consumer brand knowledge and brand choice confidence link. The proposed model was tested with structural-equation analysis. The results show that expertise and familiarity effect the positive affect. Positive affect, in turn, influences brand choice confidence. The results indicate that the processes underlying global fashion brand knowledge and brand choice confidence link are different between the consumers with overseas residence experience for more than a year and the consumers without it. The route from expertise to positive affect has a significant impact on the consumers with overseas residence experience but not on the consumers without it; however, the route from familiarity to positive affect and the path from positive affect to brand choice confidence have a greater impact on the consumers without overseas residence experience than the consumers with it. We find that the consumers with overseas residence experience favor expertise in the process underlying global fashion brand knowledge and brand choice confidence link, whereas the consumers without it favor familiarity and affect based thought.

Effect of Storytelling Marketing in Publishing Company: Focused on Facebook Case (출판사의 스토리텔링 마케팅 효과 연구: 페이스북을 중심으로)

  • Bae, Jun-Young;Oh, Kyung-Soo
    • The Journal of the Korea Contents Association
    • /
    • v.15 no.10
    • /
    • pp.92-104
    • /
    • 2015
  • Many publishing companies go to storytelling marketing through facebook in these days. Because storytelling marketing through facebook is thought for publishing company as useful marketing method in accordance with the increase of social media user. Thus, this study classified storytelling marketing type by episode, experience, anniversary, information and also analyzed the difference of cognitive reaction, emotional reaction and variables which effect to purchase intention according to each storytelling marketing type. As the results, anniversary type and information type got more positive reaction from responses rather than episode type and experience type with respect to likability, reliability, informativeness, engagement. Also engagement, likability, informativeness are revealed as major variables which effect to purchase intention of each storytelling type. Thus, storytelling marketing of publishing company through facebook need to focus on anniversary type and information type. And it is important to combine naturally the information regarding to book that publishing company want to sell with the fun, pleasure factors that story can give.

Display Types for Alleviating Negative Attitude toward Advertisements Attached to Web Articles (인터넷 신문기사에 첨부된 광고의 거부감 경감을 위한 광고 제시 방식)

  • Yu, Hyun-Jin;Lim, Seong-Taek;Chung, Jin-Gu;Lee, Ju-Hwan
    • 한국HCI학회:학술대회논문집
    • /
    • 2007.02b
    • /
    • pp.554-559
    • /
    • 2007
  • 최근 인터넷 관련 기술의 급속한 발전으로 사람들의 다양한 사회적, 경제적 행위들이 인터넷을 기반으로 확대되고 있다. 특히 우리나라의 경우 초고속 통신망의 확산과 더불어 인터넷 쇼핑몰과 상거래시장 또한 빠르게 성장하였다. 이러한 상황에서 인터넷을 매체로 하는 광고기법 또한 다양하게 적용되고 있는데, 인터넷을 통한 광고 효과를 극대화하기 위해 인터넷 신문기사 주변에 배치된 배너광고, 팝업광고 등 여러 가지 시도들이 있어왔다. 이러한 시도들은 인터넷 사용자의 편의에 대한 고려보다는 광고내용을 얼마나 잘 전달할 수 있는가에 초점이 맞추어져 있었다. 그러나 광고내용이 잘 전달된다 하더라도 소비자가 그 광고에 대해 불쾌감을 느끼게 된다면 과연 인터넷 광고효과가 높다고 말할 수 없을 것이다. 예를 들어, 팝업광고에 대한 대응책으로 개인적으로 팝업 블록커(pop-up blocker)를 사용하겠는가에 대한 설문조사 결과를 보면 사람들이 팝업 블록커를 이용해서라도 팝업광고를 피하고자 하는 비율이 77%에 달한다는 것을 알 수 있다. 실제로 Windows XP 서비스팩 2 이후의 버전은 인터넷 사용자들의 편의를 위해 자동 팝업 차단기능을 갖추고 있는 실정이다. 팝업광고를 통해 아무리 높은 정보전달 효과가 발생한다 하더라도 사용자들은 팝업광고에 대하여 거부감이나 부정적 감정을 느낄 수 있다. 그리고 광고정보가 전달된다 하더라도 팝업광고에 대한 사용자들의 불편함이 그 광고에 대한 부정적 감정으로 전이되어 광고대상에 대한 이미지에 악영향을 미칠 수 있음에 유의해야 한다. 그러므로 광고효과는 극대화하면서, 혹은 기존의 수준을 유지하면서 광고에 대한 거부감을 줄인 광고형태를 찾기 위한 다양한 노력들이 필요하다. 이를 위해 본 연구에서는 인터넷 신문기사에 첨부된 광고에 대한 사용자의 거부감을 줄일 수 있는 새로운 광고 제시 방식을 찾고자 일반적으로 사용되는 배너와 팝업 등 두 가지 광고 제시 방식과 전면에 돌출하지 않는 형태로 인터넷 신문기사의 배경에 삽입된 광고 제시 방식을 비교하였다. 그 결과, 인터넷 신문기사 영역의 주변 특정 부분(코너나 중간 부분 등)에 광고를 삽입한 배너 형태의 광고와 인터넷 신문기사 위에 광고가 돌출 등장하여 콘텐츠를 가리는 팝업 형태의 광고 제시 방식보다 새롭게 제안된 백그라운드 형태의 광고 제시 방식이 인터넷 신문기사를 읽는 사용자에게 거부감을 줄이며 동시에 광고효과를 유지할 수 있음을 확인하였다. 이러한 결과를 인터넷 광고 제시 방식으로 활용한다면 인터넷 사용자에게 콘텐츠를 방해하여 발생하는 명시적인 거부감(explicit negative attitude)을 줄이면서도 암묵적인(implicit) 광고효과를 얻을 수 있을 것이다.

  • PDF

The moderating effect of 'Jung' in service recovery process (서비스 실패 후 회복과정에서 정(情)의 조절 역할)

  • Kim, Youn Hwan
    • Management & Information Systems Review
    • /
    • v.33 no.3
    • /
    • pp.59-76
    • /
    • 2014
  • This research tries to present the role of Jung, which is well known as Koreans' traditional emotional attachment in service recovery process. Prior research on the service recovery have focused on relationship among perceived justice, recovery satisfaction and forgiveness. Especially perceived justice including distributive, procedural, and interactional justice has addressed as most important antecedents of recovery satisfaction. Although the pivotal role of emotional factors for successful service recovery has agreed by many researchers, relatively little attention has been paid to this issue. During the service recovery process, even if customer perceived recovery effort from service provider as justice one, they might feel displeasure or dissatisfaction. It means prior researches have underestimated the importance of emotional aspect, especially for Korean perspectives. In this study, we examined customer reactions to service failure and recovery process in restaurant service settings. Specifically, we focused on the moderating effect of 'Jung' on the paths between perceived justice and outcome variables such as forgiveness and recovery satisfaction.

  • PDF