基于文本信息的人物性格分析算法的研究与实现
Research and Implementation of Character Analysis Algorithm Based on Text Information

DOI: 10.12677/CSA.2019.912245, PP. 2191-2207

Keywords: 大五人格，自然语言处理，机器学习，性格预测
Big Five Personality, Natural Language Processing, Machine Learning, Character Prediction

Full-Text   Cite this paper   Add to My Lib

Abstract:

本课题研究基于文本信息分析人物性格，聚焦于静态文本来获取小说、剧本等文学作品中的人物性格，使用《平凡的世界》这一小说著作作为样本分析训练模型，结合心理学中的大五人格算法，主要采用神经网络与传统机器学习相结合的方式，通过对比doc2Vec和word2Vec + CNN两个模型的模型效果发现在预测未知人物性格时前者有着更好的表现，因此，该模型将智能分析文本这一想法变为可能，并且可通过大五人格量表将预测得分映射出人物的性格词汇，使得未来机器能够“读懂”语义，对用户画像、智能机器以及心理学的发展具有重要意义。
Based on the text information, this research focuses on the static text to obtain the characters’ characters in novels, scripts and other literary works. Using the novel “the ordinary world” as the sample analysis training model, combined with the big five personality algorithm in psychology, it mainly adopts the combination of neural network and traditional machine learning. By comparing the model effects of the two models doc2Vec and word2Vec + CNN, it is found that the former has a better performance when predicting the character of an unknown person. Therefore, the model makes the idea of intelligent text analysis possible, and the prediction score can be mapped out the characters’ character vocabulary through the big five personality scale, so that the future machine can “read” the semantics, and the user’s portrait, intelligent machine and psychological development is of great significance.

References

[1]	Mikolov, T., Sutskever, I., Chen, K., et al. (2013) Distributed Representations of Words and Phrases and Their Compo-sitionality. Neural Information Processing Systems, 3111-3119.
[2]	Mikolov, T., Chen, K., Corrado, G. and Dean, J. (2013) Efficient Estimation of Word Representations in Vector Space. Arxiv: Computation and Language.
[3]	Le, Q.V. and Mikolov, T. (2014) Distributed Representations of Sentences and Documents. International Conference on Machine Learning, 1188-1196.
[4]	Hu, J., Jin, F., Zhang, G., Wang, J. and Yang, Y. (2017) A User Profile Modeling Method Based on Word2Vec. 2017 IEEE International Conference on Software Quality, Reliability and Security Companion, Prague, Czech Republic, 25-29 July 2017, 410-414. https://doi.org/10.1109/QRS-C.2017.74
[5]	李恒超, 林鸿飞, 杨亮, 等. 一种用于构建用户画像的二级融合算法框架[J]. 计算机科学, 2018, 45(1): 157-161.
[6]	郭炜. 架构师特刊: 用户画像实践[Z]. 2017.
[7]	Yin, Z.Y., Jiang, Y. and He, J. (2017) Analysis of Mobile Internet Mul-ti-Context User Preference. Advances in Engineering Research (AER), 130, 1175-1180. https://doi.org/10.2991/fmsmt-17.2017.232
[8]	Tang, T.T., Yin, J.Y. and Zou, Y. (2017) A Method for Telecom User Portrait Modeling. Advances in Engineering Research (AER), 130, 1181-1187. https://doi.org/10.2991/fmsmt-17.2017.231
[9]	Gu, H., Wang, J., Wang, Z., Zhuang, B. and Su, F. (2018) Mod-eling of User Portrait Through Social Media. 2018 IEEE International Conference on Multimedia and Expo, San Diego, CA, 23-27 July 2018, 1-6. https://doi.org/10.1109/ICME.2018.8486595
[10]	Ouaftouh, S., Zellou, A. and Idri, A. (2015) User Profile Model: A User Dimension Based Classification. 2015 10th International Conference on Intelligent Systems: Theories and Ap-plications, Rabat, Morocco, 20-21 October 2015, 1-5. https://doi.org/10.1109/SITA.2015.7358378
[11]	Ma, Q., Muthukrishnan, S. and Simpson, W. (2016) App2Vec: Vector Modeling of Mobile Apps and Applications. 2016 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, San Francisco, CA, 18-21 August 2016, 599-606. https://doi.org/10.1109/ASONAM.2016.7752297
[12]	Tan, B., Shen, X. and Zhai, C. (2006) Mining Long-Term Search History to Improve Search Accuracy. Proceedings of the 12th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Philadelphia, PA, 20-23 August 2006, 718-723. https://doi.org/10.1145/1150402.1150493
[13]	Teevan, J., Dumais, S.T. and Horvitz, E. (2005) Personalizing Search via Automated Analysis of Interests and Activities. Proceedings of the 28th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 51, 449-456. https://doi.org/10.1145/1076034.1076111
[14]	Qiu, F. and Cho, J. (2006) Automatic Identification of User Interest for Personalized Search. Proceedings of the 15th International Conference on World Wide Web, Edinburgh, Scotland, 23-26 May 2006, 727-736. https://doi.org/10.1145/1135777.1135883
[15]	Ma, Z., Pant, G. and Sheng, O.R. (2007) Interest-Based Personal-ized Search. ACM Transactions on Information Systems, 25, Article No. 5. https://doi.org/10.1145/1198296.1198301
[16]	Shen, X., Tan, B. and Zhai, C. (2005) Implicit User Modeling for Personalized Search. Proceedings of the 14th ACM International Conference on Information and Knowledge Manage-ment, Bremen, 31 October-5 November 2005, 824-831. https://doi.org/10.1145/1099554.1099747
[17]	Teevan, J., Dumais, S.T. and Horvitz, E. (2010) Potential for Personalization. ACM Transactions on Computer-Human Interaction, 17, Article No. 4. https://doi.org/10.1145/1721831.1721835
[18]	Zhang, T., Cheng, X., Yuan, M., et al. (2016) Mining Target Users for Mobile Advertising Based on Telecom Big Data. 2016 16th International Symposium on Communications and Information Technologies, Qingdao, 26-28 September 2016, 296-301. https://doi.org/10.1109/ISCIT.2016.7751639
[19]	吴育锋, 吴胜涛, 朱廷劭, 等. 小说人物性格的文学智能分析: 以“平凡的世界”为例[J]. 中文信息学报, 2018, 32(7): 128-136.

Full-Text