基于知识图谱的金融新闻个性化推荐算法

doi:10.19678/j.issn.1000-3428.0057446

计算机工程 ›› 2021, Vol. 47 ›› Issue (6): 98-103,114. doi: 10.19678/j.issn.1000-3428.0057446

基于知识图谱的金融新闻个性化推荐算法

陶天一¹, 王清钦¹, 付聿炜¹, 熊贇¹, 俞枫², 苑博²

1. 复旦大学计算机科学技术学院上海市数据科学重点实验室, 上海 201203;
2. 国泰君安证券股份有限公司, 上海 201201

收稿日期:2020-02-20 修回日期:2020-05-19 发布日期:2020-05-27
作者简介:陶天一(1995-),男,硕士研究生,主研方向为推荐系统、机器学习;王清钦、付聿炜,硕士研究生;熊贇,教授、博士生导师;俞枫,教授级高级工程师;苑博,工程师。

Personalized Recommendation Algorithm for Financial News Based on Knowledge Graph

TAO Tianyi¹, WANG Qingqin¹, FU Yuwei¹, XIONG Yun¹, YU Feng², YUAN Bo²

1. Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University, Shanghai 201203, China;
2. Guotai Junan Securities, Shanghai 201201, China

Received:2020-02-20 Revised:2020-05-19 Published:2020-05-27
Contact: 国家自然科学基金（U1636207，U1936213）；上海市科委发展基金（19DZ1200802，19511121204）。 E-mail:17210240014@fudan.edu.cn

摘要/Abstract

摘要： 个性化新闻资讯推荐能够有效地捕捉用户兴趣，提供高质量推荐服务的能力，因而吸引了大量高黏性用户，而知识图谱则以“实体-关系-实体”的形式表示事物间的关系，通过知识图谱中实体间的关系学习到更丰富的特征及语义信息。为更好地实现金融领域新闻的个性化推荐，提出一种基于知识图谱的个性化推荐算法KHA-CNN。结合金融业知识图谱，采用基于知识的卷积神经网络和层次注意力机制得到新闻文本的特征表示，并学习用户复杂行为数据特征。在真实数据集上的实验结果表明，与Random Forest、DKN、ATRank-like算法相比，KHA-CNN算法的F1和AUC指标分别提高了2.6个和1.5个百分点。

Abstract: Personalized news information recommendation can attract a large number of highly sticky users because of its ability to effectively capture user interests and provide high-quality recommendation services.Knowledge graph represents the relationships between things in the entity-relation-entity form, which enables the learning of richer features and semantic information.To increase the quality of personalized recommendation of news in the financial field, this paper proposes a personalized recommendation algorithm, KHA-CNN, based on knowledge graph.Combined with the knowledge graph in the financial industry, a knowledge-based convolutional neural network and the hierarchical attention mechanism are used to obtain the feature representation of news texts, and to learn the features of the complex behavior data of users.Experimental results on real data sets show that compared with Random Forest, DKN, and ATRank-like algorithms, the KHA-CNN algorithm increases the F1 score by 2.6 percentange points, and the AUC indicator by 1.5 percentange points.

Key words: knowledge graph, news recommendation, attention mechanism, behavior data, knowledge representation learning

中图分类号:

TP18

陶天一, 王清钦, 付聿炜, 熊贇, 俞枫, 苑博. 基于知识图谱的金融新闻个性化推荐算法[J]. 计算机工程, 2021, 47(6): 98-103,114.

TAO Tianyi, WANG Qingqin, FU Yuwei, XIONG Yun, YU Feng, YUAN Bo. Personalized Recommendation Algorithm for Financial News Based on Knowledge Graph[J]. Computer Engineering, 2021, 47(6): 98-103,114.

https://www.ecice06.com/CN/Y2021/V47/I6/98

图/表 8

20210618183016

20210618183020

20210618183023

20210618183028

20210618183032

20210618183037

20210618183048

20210618183053

参考文献

[1] WANG Hongwei,ZHANG Fuzheng,XIE Xing,et al.DKN:deep knowledge-aware network for news recom-mendation[C]//Proceedings of IEEE World Wide Web Conference.Washington D.C.,USA:IEEE Press,2018:1835-1844.
[2] ZHOU Guorui,ZHU Xiaoqian,SONG Chengrui,et al.Deep interest network for click-through rate prediction[C]//Proceedings of the 24th ACM SIGKDDʼ18.New York,USA:ACM Press,2018:1059-1068.
[3] ZHAI Shuangfei,CHANG Kenghao,ZHANG Ruofei,et al.DeepIntent:learning attentions for online advertising with recurrent neural networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2016:1295-1304.
[4] XIONG C,POWER R,CALLAN J.Explicit semantic ranking for academic search via knowledge graph embedding[C]//Proceedings of the 26th International Conference on World Wide Web.Washington D.C.,USA:IEEE Press,2017:1271-1279.
[5] LIN Yankai,LIU Zhiyuan,SUN Maosong,et al.Learning entity and relation embedding for knowledge graph completion[C]//Proceedings of the 29th AAAI Conference on Artificial Intelligence.[S.1.]:AAAI Press,2015:576-589.
[6] BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating embedding for modeling multi-relational data[C]//Proceedings of NIPSʼ13.Cambridge,USA:MIT Press,2013:2787-2795.
[7] WANG Zhen,ZHANG Jianfeng,FENG Jianlin,et al.Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the 28th AAAI Conference on Artificial Intelligence.[S.1.]:AAAI Press,2014:465-478.
[8] JI Guoliang,HE Shizhu,XU Liheng,et al.Knowledge graph embedding via dynamic mapping matrix[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing.Washington D.C.,USA:IEEE Press,2015:687-696.
[9] CHEN Wenjie,WEN Yi,ZHANG Xin,et al.An improved TransE-based method for knowledge graph representation[J].Computer Engineering,2020,46(5):63-69,77.(in Chinese)陈文杰,文奕,张鑫,等.一种改进的基于TransE知识图谱表示方法[J].计算机工程,2020,46(5):63-69,77.
[10] KIM Y.Convolutional neural networks for sentence classification[EB/OL].[2020-01-10].https://arxiv.org/pdf/1408.5882.
[11] PAN Deyu,SONG Yurong,SONG Bo.New microblog rumor detection model based on attention mechanism[J].Journal of Chinese Computer Systems,2021,42(2):348-353.(in Chinese)潘德宇,宋玉蓉,宋波.一种新的考虑注意力机制的微博谣言检测模型[J].小型微型计算机系统,2021,42(2):348-353.
[12] WAN Meihan,XIONG Bin,ZHU Yangyong.Gene function prediction using hierarchical attention-based heterogeneous network representation learning[J].Computer Engineering,2020,46(7):43-49. 万美含,熊贇,朱扬勇.基于异质网络层次注意力机制的基因功能预测[J].计算机工程,2020,46(7):43-49.
[13] ZHOU Chang,BAI Jinze,SONG Junshuai,et al.ATRank:an attention-based user behavior modeling framework for recommendation[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence.[S.1.]:AAAI Press,2018:159-171.
[14] MA Mingyuan,NA Sen,XU Cong,et al.The graph-based broad behavior-aware recommendation system for interactive news[EB/OL].[2020-01-10].https://arxiv.org/abs/1812.00002.
[15] QIN Chuan,ZHU Hengshu,ZHU Chen,et al.DuerQuiz:a personalized question recommender system for intelligent job interview[C]//Proceedings of ACM SIGKDDʼ19.New York,USA:ACM Press,2019:2165-2173.
[16] SHI Chuan,ZHANG Zhiqing,LUO Ping,et al.Semantic path based personalized recommendation on weighted heterogeneous information networks[C]//Proceedings of the 24th ACM International on Conference on Information and Knowledge Management.New York,USA:ACM Press,2015:453-462.
[17] CATHERINE R,COHEN W.Personalized recommenda-tions using knowledge graphs:a probabilistic logic pro-gramming approach[C]//Proceedings of the 10th ACM Conference on Recommender Systems.New York,USA:ACM Press,2016:325-332.
[18] SHA Xiao,SUN Zhu,ZHANG Jie.Attentive knowledge graph embedding for personalized recommendation[EB/OL].[2020-01-10].https://arxiv.org/pdf/1910.08288.
[19] COLLOBERT R,WESTON J,BOTTOU L,et al.Natural language processing (almost) from scratch[J].Journal of Machine Learning Research,2011,12(8):2493-2537.
[20] VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[EB/OL].[2020-01-10].https://arxiv.org/abs/1706.03762.
[21] HUANG Zhiheng,XU Wei,YU Kai.Bidirectional LSTM-CRF models for sequence tagging[EB/OL].[2020-01-10].https://arxiv.org/pdf/1508.01991.
[22] RENDLE S.Factorization machines with LibFM[J].ACM Transactions on Intelligent Systems and Technology,2012,3(3):57.

选择文件类型/文献管理软件名称

选择包含的内容

基于知识图谱的金融新闻个性化推荐算法

Personalized Recommendation Algorithm for Financial News Based on Knowledge Graph

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	李惠乾, 钟柏昌. 教育知识图谱: 研究进展与未来发展——基于2013—2023年中文核心期刊载文的分析[J]. 计算机工程, 2024, 50(7): 1-12.
[2]	王炼红, 林飞鹏, 李潇瑶, 谌桂枝, 周莉. 融入课程知识图谱的KMAKT预测[J]. 计算机工程, 2024, 50(7): 23-31.
[3]	钱来, 赵卫伟. 基于对比学习和注意力机制的文本分类方法[J]. 计算机工程, 2024, 50(7): 104-111.
[4]	刘娟, 段友祥, 陆誉翕, 张鲁. 引入知识增强和对比学习的知识图谱补全[J]. 计算机工程, 2024, 50(7): 112-122.
[5]	刘建敏, 林晖, 汪晓丁. 基于图注意力机制的无地图场景轨迹预测方法[J]. 计算机工程, 2024, 50(7): 144-153.
[6]	屠乃威, 焦猛, 阎馨. 复杂环境下输电线路鸟巢目标图像检测模型[J]. 计算机工程, 2024, 50(7): 216-226.
[7]	肖慈, 徐杨, 张永丹, 冯明文, 黄易仟. 结合注意力和低光增强的夜间语义分割[J]. 计算机工程, 2024, 50(7): 271-281.
[8]	张锡英, 孙守东, 于海浩, 边继龙. 基于空间传播的多视图三维重建[J]. 计算机工程, 2024, 50(7): 293-302.
[9]	贵向泉, 刘世清, 李立, 秦庆松, 李唐艳. 基于改进YOLOv8的景区行人检测算法[J]. 计算机工程, 2024, 50(7): 342-351.
[10]	陈佳玉, 王元龙, 张虎. 基于文本知识增强的问题生成模型[J]. 计算机工程, 2024, 50(6): 86-93.
[11]	程腾腾, 姚春龙, 于晓强, 李旭, 王庆丰. 基于多头注意力机制融合常识知识的共情对话生成[J]. 计算机工程, 2024, 50(6): 94-101.
[12]	更藏措毛, 黄鹤鸣, 杨毅杰. 融合多尺度特征与上下文信息的语音增强方法[J]. 计算机工程, 2024, 50(6): 138-147.
[13]	贺姗, 蔺素珍, 王彦博, 李大威. 基于特征融合的多波段图像描述生成方法[J]. 计算机工程, 2024, 50(6): 236-244.
[14]	杨硕, 王一丁. 基于改进薄板样条运动模型的人脸动画算法[J]. 计算机工程, 2024, 50(6): 255-265.
[15]	陈晓玉, 沈晨, 沈阅, 孔德明. 基于改进SwiftNet的堆场图像实时分割网络[J]. 计算机工程, 2024, 50(6): 296-303.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于知识图谱的金融新闻个性化推荐算法

Personalized Recommendation Algorithm for Financial News Based on Knowledge Graph

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献

相关文章 15

编辑推荐

Metrics

本文评价