Predicting the Unemployment Rate Using Social Media Analysis
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
We demonstrate how social media content can be used to predict the unemployment rate, a real-worldindicator. We present a novel method for predicting the unemployment rate using social media analysis basedon natural language processing and statistical modeling. The system collects social media contents includingnews articles, blogs, and tweets written in Korean, and then extracts data for modeling using part-of-speechtagging and sentiment analysis techniques. The autoregressive integrated moving average with exogenousvariables (ARIMAX) and autoregressive with exogenous variables (ARX) models for unemployment rateprediction are fit using the analyzed data. The proposed method quantifies the social moods expressed insocial media contents, whereas the existing methods simply present social tendencies. Our model derived a27.9% improvement in error reduction compared to a Google Index-based model in the mean absolutepercentage error metric.
Abstract
We demonstrate how social media content can be used to predict the unemployment rate, a real-worldindicator. We present a novel method for predicting the unemployment rate using social media analysis basedon natural language processing and statistical modeling. The system collects social media contents includingnews articles, blogs, and tweets written in Korean, and then extracts data for modeling using part-of-speechtagging and sentiment analysis techniques. The autoregressive integrated moving average with exogenousvariables (ARIMAX) and autoregressive with exogenous variables (ARX) models for unemployment rateprediction are fit using the analyzed data. The proposed method quantifies the social moods expressed insocial media contents, whereas the existing methods simply present social tendencies. Our model derived a27.9% improvement in error reduction compared to a Google Index-based model in the mean absolutepercentage error metric.
참고문헌 (13)
- N. Askitas, "Google econometrics and unemployment forecasting", Applied Economics Quarterly, 55(2), pp.107~120 (2009)[DOI]
- 'Google it!' Forecasting the US unemployment rate with a Google job search index, "F. D'Amuri", FEEM, ~, pp.FEEM Working Paper No. 31 (2010)
- J. Pavlicek, "Nowcasting unemployment rates with google searches: evidence from the visegrad group countries", PloS One, 10(5) (2015)
- P. S. Dodds, "Temporal patterns of happiness and information in a global social network: Hedonometrics and Twitter", PloS One, 6(12) (2011)
- Using social media to add depth to unemployment statistics, UN Global Pulse White Paper, "United Nations Global Pulse", UN Global Pulse, ~ (2011)
- V. Lampos, "Nowcasting events from the social web with statistical learning", ACM Transactions on Intelligent Systems and Technology, 3(4) (2012)
- A. Signorini, "The use of Twitter to track levels of disease activity and public concern in the US during the influenza A H1N1 pandemic", PloS One, 6(5) (2011)[DOI]
- 임수종, "Domain-Adaptation Technique for Semantic Role Labeling with Structural Learning", ETRI Journal, 36(3), pp.429~438 (2014), 한국전자통신연구원[DOI]
- L. Velikovich, "The viability of web-derived polarity lexicons", Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pp.777~785 (2010), Association for Computational Linguistics
- 이공주, "Extracting Multiword Sentiment Expressions by Using a Domain-Specific Corpus and a Seed Lexicon", ETRI Journal, 35(5), pp.838~848 (2013), 한국전자통신연구원
- C. Strapparava, "WordNet affect: an affective extension of WordNet", Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC), pp.1083~1086 (2004)
- A. Esuli, "SentiWordNet: a publicly available lexical resource for opinion mining", Proceedings of the 6th International Conference on Language Resources and Evaluation (LREC), pp.417~422 (2006)
- G. E. P. Box, "Time Series Analysis: Forecasting and Control" (1976), Prentice Hall