메뉴 건너뛰기
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)
고객센터 ENG
주제분류

논문 기본 정보

저자정보
(Seoul National University) (Seoul National University) (Seoul National University) (Seoul National University) (Seoul National University)
저널정보
대한산업공학회 대한산업공학회 추계학술대회 논문집 2019년 대한산업공학회 추계학술대회
오류 신고하기

피인용 0

검색

    초록·키워드

    The study compares the outcome of semantic network analysis based on consumer reviews in two different units of text: paragraph and sentence. Taking Apple Watch Series 4 as a case study, review data was collected from Amazon. The overall process consists of text preprocessing, centrality measures, and cluster analysis. In centrality measures, consumer reviews in paragraph unit can yield more affective adjectives that reveal emotions or feelings of consumers towards the product. On the other hand, more nouns representing product features can be generated from reviews in sentence unit. Comparing the results of cluster analysis, the performance of review data in sentence unit is better. Topics can be created in each cluster based on reviews in sentence unit, and the average number of related words in clusters based on reviews in sentences are bigger. In conclusion, the sentence unit is suggested for semantic analysis when the information about significant product features and topics is required, and the paragraph unit is suggested when the emotions or feelings of users toward the product are required.

    최근 본 자료 전체보기

      UCI(KEPA) : I410-ECN-0101-2019-530-001291961