메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술저널
저자정보
김현숙 (배재대학교)
저널정보
한국생활과학회 한국생활과학회지 한국생활과학회지 제32권 제6호
발행연도
2023.12
수록면
767 - 782 (16page)
DOI
10.5934/kjhe.2023.32.6.767

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
Fashion products should encompass a wide variety of styles to suit individual preferences. Therefore, online retailers should identify diverse consumer preferences and satisfaction-dissatisfaction factors early through online review analysis. This enhances consumer satisfaction and improves product planning and marketing efficiency. However, product reviews often cover multiple topics within a single document, and due to the extensive nature of unstructured data with varying expressions and lengths, it is challenging to effectively harness them for practical purposes. The objective of this study was to categorize fashion product reviews and to create sentiment prediction models for establishing systematic analysis. The specific research includes: first, classifying online fashion product reviews; and second, building a sentiment prediction model and validating it. The Amazon review dataset 2018 including 881,895 data entries was used. Fashion product reviews were categorized into three groups using the k-means clustering algorithm; "Size & Fit," "Quality & Price," and "Appearance." Validation of significance was conducted using ANOVA mean analysis, post hoc analysis, and silhouette score. To construct sentiment prediction models for fashion product online reviews, various embeddings and algorithms were combined and tested. Embeddings included Count Vectorization, TF-IDF, and Word2Vec, while algorithms comprised SVC, logistic regression, random forest classifier, bagging classifier, and multinomial NB. Comparative analysis against a bi-directional sequence LSTM model revealed that the bi-directional LSTM model achieved the highest accuracy of 0.94. In conclusion, this study proposed models for categorizing fashion product reviews and establishing a sentiment prediction model, thus providing a schema for efficient review-based product planning and marketing strategies.

목차

Abstract
Ⅰ. 서론
Ⅱ. 이론적 배경
Ⅲ. 연구모델 및 연구방법
Ⅳ. 결과 및 논의
Ⅴ. 결론 및 제언
REFERENCES

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문의 저자 정보

이 논문과 함께 이용한 논문

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-151-24-02-089266959