지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 발행연도
- 2019.4
- 수록면
- 105 - 114 (10page)
- DOI
- 10.5143/JESK.2019.38.2.105
이용수
초록· 키워드
오류제보하기
Objective: The primary aim of this study was to examine the sentiment expression according to gender and user activity level with a particular focus on the social networking site of Twitter.
Background: With the vast and ever-growing popularity of social networking services, sentiment analysis on SNS has become widely used in data science for analysis of user`s feedback and opinion mining.
Method: The messages posted from 13.4 million twitter users (6.9 million male users) for 11 months were analyzed and the message polarity, sentiment strength and the type (evaluative/factual) of messages were explored.
Results: The results showed that the average sentiment strength of female users was significantly (p <0.01) higher than that of male users and the average sentiment strength of highly active male users was lowest among groups. It also showed that the highly active male users tend to post more negative messages than other groups and female users express significantly more positive sentiment than male users for both highly and less active user levels.
Conclusion: It implies that the gender and activity level differences of users should be considered in sentiment analysis on social media data to gain valuable insights.
Application: The results of this study could be used as quantitative, empirical data and design guidelines for developing sentiment analysis and opinion mining systems on SNS.
Background: With the vast and ever-growing popularity of social networking services, sentiment analysis on SNS has become widely used in data science for analysis of user`s feedback and opinion mining.
Method: The messages posted from 13.4 million twitter users (6.9 million male users) for 11 months were analyzed and the message polarity, sentiment strength and the type (evaluative/factual) of messages were explored.
Results: The results showed that the average sentiment strength of female users was significantly (p <0.01) higher than that of male users and the average sentiment strength of highly active male users was lowest among groups. It also showed that the highly active male users tend to post more negative messages than other groups and female users express significantly more positive sentiment than male users for both highly and less active user levels.
Conclusion: It implies that the gender and activity level differences of users should be considered in sentiment analysis on social media data to gain valuable insights.
Application: The results of this study could be used as quantitative, empirical data and design guidelines for developing sentiment analysis and opinion mining systems on SNS.
목차
1. Introduction
2. Background
3. Method
4. Results
5. Conclusion
References
참고문헌 (27)
참고문헌 신청
Anderson, C. / 2006 / The long tail: Why the future of business is selling less of more / Hyperion
Roy F. Baumeister / 2001 / Bad is Stronger than Good / Review of General Psychology 5(4):323~370
Jyh-Shen Chiou / 2003 / Should a company have message boards on its Web sites? / Journal of Interactive Marketing 17(3):50~61
Shu-Chuan Chu / 2015 / Determinants of consumer engagement in electronic word-of-mouth (eWOM) in social networking sites / International Journal of Advertising 30(1):47~75
Sun-Jae Doh / 2009 / How Consumers Evaluate eWOM (Electronic Word-of-Mouth) Messages / CyberPsychology & Behavior 12(2):193~197
Roy F. Baumeister / 2001 / Bad is Stronger than Good / Review of General Psychology 5(4):323~370
Jyh-Shen Chiou / 2003 / Should a company have message boards on its Web sites? / Journal of Interactive Marketing 17(3):50~61
Shu-Chuan Chu / 2015 / Determinants of consumer engagement in electronic word-of-mouth (eWOM) in social networking sites / International Journal of Advertising 30(1):47~75
Sun-Jae Doh / 2009 / How Consumers Evaluate eWOM (Electronic Word-of-Mouth) Messages / CyberPsychology & Behavior 12(2):193~197
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
인스타그램 해시태그를 이용한 사용자 감정 분류 방법
멀티미디어학회논문지
2015 .11
-
User sentiment analysis by Electric Vehicle based on Aspect-Based Sentiment Analysis
대한인간공학회 학술대회논문집
2020 .10
-
Review on the Usage of Deep Learning Models in Multi-modal Sentiment Analysis
IEIE Transactions on Smart Processing & Computing
2020 .12
-
국내 주요 10대 기업에 대한 국민 감성 분석 : 다범주 감성사전을 활용한 빅 데이터 접근법
지능정보연구
2016 .09
-
Sentiment Analysis using Various Machine Learning Techniques: A Review
IEIE Transactions on Smart Processing & Computing
2022 .04
-
Bi-LSTM 기반의 한국어 감성사전 구축 방안
지능정보연구
2018 .12
-
재무 보고서의 키워드 검출 기반 딥러닝 감성 분석 기법
한국정보통신학회논문지
2020 .05
-
Analyzing Dissatisfaction Factors of Weather Service Users Using Twitter and News Headlines
International JOURNAL OF CONTENTS
2019 .12
-
SNS 데이터 분석을 위한 감성용어 분류기법 연구
한국정보과학회 학술발표논문집
2015 .12
-
SNS 특성과 만족도, 수용의도간의 관련성 연구
한국컴퓨터정보학회논문지
2015 .11
-
집단지성을 이용한 한글 감성어 사전 구축
지능정보연구
2015 .06
-
SNS 빅데이터의 상대 유사도를 반영한 감성 분석 시스템 설계
한국정보과학회 학술발표논문집
2019 .06
-
Impact of Firm-specific Textual Sentiment on Credit spreads
금융정보연구
2024 .02
-
뉴스기사를 이용한 소비자의 경기심리지수 생성
지능정보연구
2017 .09
-
소셜 미디어에서의 사용자 성별, 사용자 그룹과 자기노출간의 연관성 연구
한국컴퓨터정보학회논문지
2018 .04
-
평점과 리뷰 텍스트 감성분석을 결합한 추천시스템 향상 방안 연구
지능정보연구
2019 .03
-
Sentiment Analysis Main Tasks and Applications: A Survey
JIPS(Journal of Information Processing Systems)
2019 .01
-
Product Recommendation System
INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING
2019 .06
-
딥러닝 LSTMs 기반 자연어 감성분석 모델을 활용한 거주자의 감성분류
대한건축학회 학술발표대회 논문집
2019 .10
-
소셜 이미지에서의 사용자 감성 인식을 위한 시각 특징 분석
한국정보과학회 학술발표논문집
2015 .06
이 논문의 저자 정보
이 논문과 함께 이용한 논문
소셜미디어 데이터를 활용한 제품기회의 변화 추적
정재민
,
윤장혁
대한산업공학회 춘계공동학술대회 논문집
2019
.04
내용분석방법을 통한 소비자행복 분석 - 소확행 트렌드를 중심으로 -
이제성
,
이준영
문화와융합
2019
.06
딥러닝을 활용한 예술로봇의 관객 감정 파악과 공감적 표정 생성
노진아
한국콘텐츠학회 종합학술대회 논문집
2019
.05
빅데이터 분석을 통한 디저트 카페 개념에 대한 탐색적 연구
김예지
,
김학선
Culinary Science & Hospitality Research
2019
.05
공유숙박 서비스 기업의 감성분석을 통한 이미지 변화
박흥식
,
김주일
Culinary Science & Hospitality Research
2019
.05
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2019-530-000666995