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
학술대회자료
저자정보
Yeong Hyeon Gu (Sejong University) Seong Joon Yoo (Sejong University) Yun Hwan Kim (Sejong University) Zhegao Piao (Sejong University)
저널정보
한국정보통신학회 INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING 2015 INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING Vo.7 No.1
발행연도
2015.6
수록면
139 - 144 (6page)

이용수

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

초록· 키워드

오류제보하기
Economic forecasting has been made usually based on quantitative data such as economic indexes. News contents are also one of significant factors influencing the market, but they have been excluded from the process of forecasting. In order to solve this problem, research is being conducted actively on collecting, analyzing, and utilizing news for economic forecasting using the latest text mining techniques. However, economic news contain not only economy-related contents but also those irrelevant to economic forecasting such as product/service promotions, introductions to new products, and appointment orders. Such irrelevant contents may cause noise and lower the performance of text-based economic forecasting. As an effort to solve this problem, this study attempted to sort out promotional news from economic news. For this purpose, news were collected using a Web crawler, and collected documents were manually divided into and labeled as economic news and promotional news. Then, term vectors were built using the frequency of words, and then raw data were classified through SVM using the terms as features. Performance was tested through 10-cross validation, and according to the results of the experiment, when the TF-IDF technique was applied to vector representation with feature extraction as Bigram, F-measure was highest as 0.95. The promotional news classifier developed in this study is expected to be applicable as a core technology for text mining-based economic forecasting.

목차

Abstract
I. INTRODUCTION
II. SYSTEM MODEL AND METHODS
III. RESULTS
IV. DISCUSSION AND CONCLUSIONS
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

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-ECN-0101-2018-004-000970999