DOI QR코드

DOI QR Code

A Design of SNS Emotional Information Analysis Strategy based on Opinion Mining

오피니언 마이닝 기반 SNS 감성 정보 분석 전략 설계

  • Received : 2015.12.01
  • Accepted : 2015.12.19
  • Published : 2015.12.30

Abstract

The opinion mining technique which analogize significant information from SNS message is increasingly important because opinions communicated through SNS are increasing. This paper propose SEIAS(SNS Emotional Information Analysis Strategy) based on opinion mining that analogize emotional information from SNS setting a different weight according to position of antonym and adverb. Firstly, the proposed SEIAS constructs a emotion dictionary for opinion mining analysis, Secondly, it collects SNS data on real time, compare it with emotion dictionary and calculates opinion value of SNS data. Specially, it increases the precision of opinion analysis result compared to the existing SO-PMI because it sets up the different value according to the position of antonym and adverb when it calculates the opinion value of data.

현재, SNS으로 소통되는 의견들이 증가하고 있기 때문에 SNS 메시지로부터 의미 있는 정보를 유추해내는 오피니언 마이닝(Opinion mining) 기술이 중요해지고 있다. 본 논문은 반의어와 부사의 위치에 따라 가중치를 다르게 설정하여 SNS의 감성 정보를 정확하게 추출하는 오피니언 마이닝 기반 SNS 감성 정보 분석 전략(SEIAS, SNS Emotional Information Analysis Strategy)을 제안한다. 제안하는 SEIAS(SNS Emotional Information Analysis Strategy)는 첫째, 오피니언 마이닝 분석에 필요한 감성사전을 구축하고, 둘째, SNS 데이터를 실시간으로 수집하고, 수집된 SNS 데이터와 감성사전를 비교하여 SNS 데이터의 의견값을 산출한다. 특히, 데이터의 의견값을 산출할 때, 반의어, 부사의 위치에 따라 가중값을 다르게 설정함으로써 기존의 SO-PMI와 비교하였을 때 오피니언 분석결과의 정확도를 향상시켰다.

Keywords

References

  1. Gyung-Mi Park, Ho-Gun Park, Hyoung-Gon Kim, Hee-Dong Ko, "A Study of Opinion mining on SNS," Communication of KIISE, vol.29, no.11, pp.54-60, 2011.
  2. Jung-Yeol Seo, Chan Koh, "Big Data Analysis by Sensitivity Analysis," Journal of the Society of Convergence Knowledge, vol.2, no.1, pp.15-21, 2014.01.
  3. Eun-Hee Jeong, Byung-Kwan Lee, Yusrina Tifani, "A Emotion Information Analysis of SNS using Opinion Mining", the Korea Institute of Information, Electronics, and Communication Technology, vol.8, no.2, pp.199-201, 2015.
  4. Seung-Woo Kim, Nam-Gyu Kim, "A Study of Emotional Dictionary Application Effect of Opinion Classifier," J Intell Inform Syst, vol.20, no.1, pp.133-148, 2014.33. https://doi.org/10.13088/JIIS.2014.20.1.133
  5. P. Turney, M. Littman, "Measuring praise and criticism:inference of semantic orientation from association," Proceedings of ACL-02, 40th Annual Meeting of the Association for Computational Linguistics, pp.417-424, 2002.
  6. Ji-Hoon Seo, Hye-Jin Jo, Jin-Tak Choi, "Design for Opinion Dictionary of Emotion Applying Rules for Antonym of Korean Grammar", Journal of KIIT, vol.13, no.2, pp.109-117, 2015.
  7. Sang-Il Song, Dong-Joo Lee, Sang-Goo Lee, "Identifying Sentiment Polarity of Korean Vocabulary Using PMI," Korea Computer Congress 2010, vol.37, no.1, pp.260-265, 2010.

Cited by

  1. A SNS Data-driven Comparative Analysis on Changes of Attitudes toward Artificial Intelligence vol.14, pp.12, 2016, https://doi.org/10.14400/JDC.2016.14.12.173
  2. Developing a hybrid collaborative filtering recommendation system with opinion mining on purchase review 2017, https://doi.org/10.1177/0165551517692955
  3. 소셜 미디어 데이터 분석을 활용한 빅데이터에 대한 인식 변화 비교 분석 vol.6, pp.7, 2017, https://doi.org/10.3745/ktsde.2017.6.7.371
  4. 교육정책관련 여론탐색을 위한 소셜미디어 감정분석 연구 vol.24, pp.4, 2017, https://doi.org/10.22693/niaip.2017.24.4.003
  5. 스마트 공장에서 의사결정 모델을 이용한 순차 마이닝 기반 제조공정 vol.9, pp.3, 2018, https://doi.org/10.15207/jkcs.2018.9.3.053
  6. Discovery of knowledge of associative relations using opinion mining based on a health platform vol.24, pp.5, 2020, https://doi.org/10.1007/s00779-019-01231-2