유튜브 기반 데이터 분석을 통한 주가 선행성 분석
Stock Price Priorities Analysis through YouTube-Based Data Analysis
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
주로 감성 분석을 위해서 구글 검색 키워드 분석, 트위터 댓글 분석 등과 같은 매체를 활용한다. 최근에 이러한 매체에 비해서 유튜브의 사용 빈도가 매우 높은데 영상 미디어 자료가 주된 콘텐츠다 보니 이를 이용한 감성 분석에 관한 연구는 쉽게 찾아볼 수 없다. 주가의 투자자들은 자신이 투자한 자산의 가치가 변동하면서 심리적 기대 또는 불안 등에 따라서 유튜브 영상을 검색할 수 있고 그 검색빈도는 심리 변화에 따라 차이가 있을 것으로 판단된다. 따라서 본 연구에서는 크롤링 알고리즘을 통해서 유튜브 채널들의 자료를 수집하고 이를 ETF 주식 데이터와 인과 분석을 수행했다. 그 결과 유튜브의 조회 수와 같은 데이터는 금융 시장을 선행한다는 것을 통계적으로 입증했으며, 특히 유튜브의 검색 빈도의 증가가 자산 거래량에 강한 선행성을 보였다. 본 연구는 향후 수행될 감성 분석에 관한 연구에 참고문헌이 되기를 기대한다.
Abstract
In general, media such as Google search keyword analysis and Twitter comment analysis are used for emotional analysis. Recently, compared to these, YouTube is used very frequently, and since video media data is the main content, research on emotional analysis using it is not easy to find. Investors in financial products such as stocks can search YouTube videos according to psychological expectations or anxiety as the value of their assets changes, and the frequency of searches is expected to vary depending on psychological changes. Therefore, in this study, data from YouTube channels were collected through a crawling algorithm, and ETF stock data and causal analysis were performed. As a result, it was statistically proven that data such as YouTube's number of views precede the financial market, and in particular, the increase in YouTube's search frequency showed strong precedence over asset transactions. This study is expected to serve as a reference for future research on emotional analysis.
참고문헌 (26)
- 황낙건, "OTT 플랫폼의 썸네일 서비스 유형이 지속이용의도에 미치는 영향 : 유튜브 이용자를 중심으로", 한국엔터테인먼트산업학회논문지, 16(3), pp.13~27 (2022), 한국엔터테인먼트산업학회
- M. Thelwall, "Social media analytics for YouTube comments : potential and limitations", International Journal of Social Research Methodology, 21(3), pp.303~316 (2018)
- L. Yue, "A survey of sentiment analysis in social media", Knowledge and Information Systems, 60, pp.617~663 (2019)
- S. Chan, "Sentiment analysis in financial texts", Decision Support Systems, 94, pp.53~64 (2017)
- X. Li, "News impact on stock price return via sentiment analysis", Knowledge-Based Systems, 69, pp.14~23 (2014)
- J. L. Seng, "The association between stock price volatility and financial news – a sentiment analysis approach", Kybernetes, 46(8) (2017)
- S. Krishnamoorthy, "Sentiment analysis of financial news articles using performance indicators", Knowledge and Information Systems, 56, pp.373~394 (2018)
- E. Cambria, "Affective computing and sentiment analysis", Socio-Affective Computing, 5 (2017)
- U. P. Gurav, "Sentiment aware stock price forecasting using an SA-RNN-LBL learning model", Engineering, Technology & Applied Science Research, 10(5), pp.6356~6361 (2020)
- D.Michael, "Google search-based metrics, policy-related uncertainty and macroeconomic conditions", Applied Economics Letters, 22(10), pp.801~807 (2015)
- M. Y. Huang, "Forecasting stock market movements using Google trend searches", Empirical Economics, 59, pp.2821~2839 (2020)
- Y. Liu, "Composite leading search index : a preprocessing method of internet search data for stock trends prediction", Annals of Operations Research, 234, pp.77~94 (2015)
- M. Bank, "Google search volume and its influence on liquidity and returns of german stocks", Financial Markets and Portfolio Management, 25, pp.239~264 (2011)
- G. P. Smith, "Google internet search activity and volatility prediction in the market for foreign currency", Finance Research Letters, 9(2), pp.103~110 (2012)
- M. S. Checkley, "The hasty wisdom of the mob : How market sentiment predicts stock market behavior", Expert Systems with Applications, 77, pp.256~263 (2017)
- X. Zhang, "Predicting stock market indicators through Twitter", Procedia-Social and Behavioral Sciences, 26, pp.55~62 (2011)
- M. Venkataraman, "Does internet search intensity predict house prices in emerging markets? A case of India", Property Management, 36(1), pp.103~118 (2018)
- E. Beracha, "Forecasting residential real estate price changes from online search activity", Journal of Real Estate Research, 35(3), pp.283~312 (2013)
- S. Mihaela, "Improving unemployment rate forecasts at regional level in Romania using Google Trends", Technological Forecasting and Social Change, 155 (2020)
- H. Jelodar, "A NLP framework based on meaningful latent-topic detection and sentiment analysis via fuzzy lattice reasoning on youtube comments", Multimedia Tools and Applications, 80, pp.4155~4181 (2020)
- M. Ehliz, "Prediction accuracy of YouTube influencers measured against subscriber counts", Journal of Student Research, 11(3) (2022)
- A. Shojaie, "Granger causality : A review and recent advances", Annual Review of Statistics and Its Application, 9, pp.289~319 (2022)
- W. Enders, "Improved critical values for the Enders-Granger unit-root test", Applied Economics Letters, 8(4), pp.257~261 (2001)
- Z. Adali, "Assessing the stochastic behavior of fishing grounds footprint of top ten fishing countries", Regional Studies in Marine Science, 63 (2023)
- S. Tang, "Measurement and management of interest rate risk of commercial banks : Based on VaRGARCH model of a case study of SHIBOR", Scientific and Social Research, 4(1) (2022)
- J. H. Kim, "A study on estimation and prediction of vector time series model using financial big data", Turkish Journal of Computer and Mathematics Education, 12(5) (2021)