基于Item2Vec负采样优化的专题地图产品个性化推荐方法研究

doi:10.12082/dqxxkx.2020.190668

Abstract

Abstract:

Establishing a user preference recommendation model suitable for thematic map product search is one of the effective ways to improve the quality of the thematic map products. In the thematic map product recommendation scenario, there are serious problems of content cold-start and sparse comment data. The existing recommendation algorithms cannot recommend thematic map products with different features for specific types of users, resulting in users' limited preference for obtaining preference information from the thematic maps. Hence, this paper presents a user preference recommendation method based on the combination of CBOW with Negative Sampling and Iten2Vec based on Word2Vec. Firstly, calculating implicit ratings of the interaction behavior data in the user behavior log, to replace sparse user ratings in thematic disaster scenarios; Secondly, extracting context-aware feature information of central thematic map based on CBOW model with Negative Sampling. By controlling the ratio of positive and negative samples to 1:2, the prediction accuracy of the potential score of the target thematic map is improved; Finally, mapping Thematic CMaps with user behavior characteristics information to vector space via Item2Vec, calculating the user's similarity matrix to the thematic map and completing recommendations based on user preference. Test results on thematic map scoring experiment dataset Thematic CMaps and four validation dataset MovieLens show that, compared with the four traditional recommendation algorithm of LFM, Personal Rank, Content Based, and SVD, this proposed method can effectively improve the precision potential scoring, and the highest recommending performance is 27.85%. Compared with Item2Vec with Huffman sampling method and YouTubeNet two neural network recommendation algorithms, the score prediction accuracy has improved to a certain extent, and the recommendation performance has been continuously improved, reaching the maximums of 2.97% and 5.78%. Taking the singular value decomposition (SVD) of the classic algorithm as an example, in the increasing data subset after the segmentation of MovieLens-20M dataset, the score prediction accuracy and performance of the method used in this paper are better than SVD method.

Key words: map personalized recommendation, thematic map products retrieval, deep learning, negative sampling method, Item2Vec, CBOW model, user event behavior, implicit ratings

MAO Wenshan, ZHAO Hongli, SUN Fengjiao, JIANG Yunzhong, JIANG Qian, ZHU Yanru. Personalized Recommendation Method of Thematic Map Products based on Item2Vec with Negative Sampling Optimization[J].Journal of Geo-information Science, 2020, 22(11): 2128-2139.DOI:10.12082/dqxxkx.2020.190668

Figures/Tables 10

Fig. 1

Tab. 1

Fig. 2

Tab. 2

Fig. 3

Fig. 4

Tab. 4

Tab. 5

Tab. 6

Tab. 7

Two recommended results comparison between Item2Vec (Negative Sampling) and SVD"

种子专题地图	Item2Vec(负采样)—Top5	SVD—Top5
107国道线路地图——交通地图\|国道线路图	109国道线路地图——交通地图\|国道线路图	全国国道线路图——交通地图\|国道线路图
	全国国道线路图——交通地图\|国道线路图	102国道线路地图——交通地图\|国道线路图
	全国国道分布图——交通地图\|国道线路图	104国道线路地图——交通地图\|国道线路图
	102国道线路地图——交通地图\|国道线路图	318国道全程示意图——交通地图\|国道线路图
	318国道全程示意图——交通地图\|国道线路图	317国道线路地图——交通地图\|国道线路图
四川省宜宾市泸州市交通地图——交通地图\|公路地图集	四川省雅安市阿垻州交通地图——交通地图\|公路地图集	宁夏交通地图全图——交通地图\|公路地图集
	四川省眉山市乐山市交通地图——交通地图\|公路地图集	四川省眉山市乐山市交通地图——交通地图\|公路地图集
	四川省交通地图全图——交通地图\|公路地图集	四川省交通地图全图——交通地图\|公路地图集
	四川省成都市交通地图——交通地图\|公路地图集	湖南省长沙株洲衡阳怀化交通地图——交通地图\|公路地图集
	四川南充德阳达州自贡内江交通地图——交通地图\|公路地图集	四川高速公路地图2017版——交通地图\|高速公路网
四川高速公路地图2017版— 交通地图\|高速公路网	四川18条高速公路线路规划图2017——交通地图\|高速公路网	四川省收费公路主线站点分布图——交通地图\|高速公路网
	云南高速公路地图2017版——交通地图\|高速公路网	国家高速公路网线路图——交通地图\|高速线路图
	国家高速公路网规划方案图——交通地图\|高速公路网	国家高速公路网布局——交通地图\|高速线路图
	国家高速公路网线路图——交通地图\|高速线路图	四川18条高速公路线路规划图2017——交通地图\|高速公路网
	甘肃高速公路地图2017版——交通地图\|高速公路网	云南高速公路地图2017版——交通地图\|高速公路网

Tab. 7

References 27

[1]	Aleksandra K M, Mirjana I, Nanopoulos A. Recommender systems in e-learning environments: A survey of the state-of-the-art and possible extensions[J]. Artificial Intelligence Review, 2015,44(4):571-604.
[2]	郑束蕾, 陈毓芬, 杨春雷, 等. 地图个性化认知适合度的眼动试验评估[J]. 测绘学报, 2015,44(s1):27-35.
	[ Zheng S L, Chen Y F, Yang C L, et al. Quantitative evaluation of personalized cognition suitability on maps by eye movement experiment[J]. Acta Geodaetica et Cartographica Sinica, 2015,44(s1):27-35. ]
[3]	方潇, 李萌, 包芃, 等. 基于眼动实验的个性化地图推荐模型探讨[J]. 地理空间信息, 2015,13(1):167-170.
	[ Fang X, Li M, Bao F, et al. Discussion on personalized map recommendation model based on eye movement experiment[J]. Geospatial Information, 2015,13(1):167-170. ]
[4]	冯天文, 李轶鲲, 刘涛, 等. 语义扩散检索方法研究——以火灾应急图组库为例[J]. 测绘科学, 2018,43(12):115-121.
	[ Feng T W, Li Y K, Liu T, et al. Research on semantic spreading retrieval method: A case study of fire emergency map base[J]. Science of Surveying and Mapping, 2018,43(12):115-121. ]
[5]	Koren Y, Bell R, Volinsky C. Matrix factorization techniques for recommender systems[J]. Computer, 2009,42(8):30-37.
[6]	Lang K. NewsWeeder: Learning to filter net-news [C]// Proceedings of the Twelfth International Conference on Machine Learning, Tahoe City, California, July 9-12, 1995: 331-339.
[7]	Almahairi A, Kastner K, Cho K, et al. Learning distributed representations from reviews for collaborative filtering [C]// RecSys'15: Proceedings of the 9th ACM Conference on Recommender Systems, September 2015: 147-154.
[8]	姜波, 张晓筱, 潘伟丰. 基于二部图的服务推荐算法研究[J]. 华中科技大学学报(自然科学版), 2013,41(s2):93-99.
	[ Jiang B, Zhang X Y, Pan W F. Bipartite graph-based service recommendation method study[J]. Journal of Huazhong University of Science and Technology (Nature Science Edition), 2013,41(s2):93-99. ]
[9]	黄立威, 江碧涛, 吕守业, 等. 基于深度学习的推荐系统研究综述[J]. 计算机学报, 2018,427(7):191-219.
	[ Huang L W, JiangB T, Lv S Y, et al. Survey on deep learning based recommender systems[J]. Chinese Journal of Computers, 2018,427(7):191-219. ]
[10]	吴彦文, 刘闯. 基于用户偏好和可疑度的推荐方法研究[J]. 计算机应用研究, 2018,35(12):118-120.
	[ Wu Y W, Liu C. Research on recommendation method based on user preference and suspicious degree[J]. Application Research of Computers, 2018,35(12):118-120. ]
[11]	Barkan O, Koenigstein N. Item2Vec: Neural item embedding for collaborative filtering [C]// Proceedings of IEEE International Workshop on Machine Learning for Signal Processing, Washington D.C., USA: IEEEPress, 2016: 1-6.
[12]	陈晋音, 吴洋洋, 林翔. 基于图过滤的快速密度聚类双层网络推荐算法[J]. 控制理论与应用, 2019,36(4):542-552.
	[ Chen J Y, Wu Y Y, Lin X. Double layered recommendation algorithm based on fast density clustering with graph-based filtering & Applications[J]. Control Theory & Applications, 2019,36(4):542-552. ]
[13]	黄金超, 张佳伟, 陈宁, 等. 基于偏好度特征构造的个性化推荐算法[J]. 上海交通大学学报, 2018,52(7):770-776.
	[ Huang J C, Zhang J W, Chen N, et al. Preference degree based personalized recommendation algorithm[J]. Journal of Shanghai Jiaotong University, 2018,52(7):770-776. ]
[14]	张敏, 丁弼原, 马为之, 等. 基于深度学习加强的混合推荐方法[J]. 清华大学学报(自然科学版), 2017,57(10):1014-1021.
	[ Zhang M, Ding B Y, Ma W Z, et al. Hybrid recommendation approach enhanced by deep learning[J]. Journal of Tsinghua University (Science and Technology), 2017,57(10):1014-1021. ]
[15]	陈冬林, 聂规划, 刘平峰. 基于网页语义相似性的商品隐性评分算法[J]. 系统工程理论与实践, 2006,26(11):98-102.
	[ Chen D L, Nie G H, Liu P F. An algorithm for goods implicit rating based on web pages semantic similarity[J]. System Engineering Theory and Practice, 2006,26(11):98-102. ]
[16]	Kenter T, Borisov A, De R M. Siamese CBOW: Optimizing word embeddings for sentence representations [C]// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Berlin, Germany, August 7-12, 2016: 941-951.
[17]	刘淑涵, 王艳东, 付小康. 利用卷积神经网络提取微博中的暴雨灾害信息[J]. 地球信息科学学报, 2019,21(7):1009-1017.
	[ Liu S H, Wang Y D, Fu X K. Extracting rainstorm disaster information from microblogs using convolutional neural network[J]. Journal of Geo-information Science, 2019,21(7):1009-1017. ]
[18]	Yao W, He J, Huang G, et al. A graph-based model for context-aware recommendation using implicit feedback data[J]. World Wide Web, 2015,18(5):1351-1371.
[19]	Breese J S, Heckerman D, Kadie C. Empirical analysis of predictive algorithms for collaborative filtering [C]// U-AI'98: Proceedings of the Fourteenth conference on Uncertainty in Artificial Intelligence, July 1998: 43-52.
[20]	Kenter T, Borisov A, De R.M. Siamese CBOW: Optimizing word embeddings for sentence representations[J]. ACL 2016, June 2016,2016:941-951.
[21]	Qin P, Xu W, Guo J. A novel negative sampling based on TFIDF for learning word representation[J]. Neurocomputing, 2015,177:257-265.
[22]	Mikolov T, Sutskever I, Kai C, et al. Distributed representations of words and phrases and their compositionality[J]. Advances in Neural Information Processing Systems, 2013,26:3111-3119.
[23]	Bansal B, Srivastava S. Sentiment classification of online consumer reviews using word vector representations [C]// Procedia Computer Science, 2018: 1147-1153.
[24]	Karumur R P, Nguyen T T, Konstan J A. Exploring the value of personality in predicting rating behaviors: a study of category preferences on MovieLens [C]// Proceedings of the 10th ACM Conference on Recommender Systems, 2016: 139-142.
[25]	Aggarwal C C. Recommender Systems \|\| Evaluating Recommender Systems[M]. New York: Recommender Systems, 2016.
[26]	Koren Y. Factorization meets the neighborhood: A multifaceted collaborative filtering model [C]// Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Las Vegas, Nevada, USA, August 24-27, 2008, ACM, 2008: 426-434.
[27]	Christian Ü, Christopher K, Veselin R, et al. Recommendations in a heterogeneous service environment[J]. Multimedia Tools and Applications, 2013,62(3):785-820.

用户ID	内容ID	事件行为次数				浏览时间/s
用户ID	内容ID	浏览行为	描述性行为	属性行为	决定性行为	浏览时间/s
1494590	60287	1	1	3	1	83

事件行为	释义	权重分配
浏览行为	次级评分	50 > (w₃×1)
描述性行为	中等评分	50 < (w₃×3)
属性行为	积极评分	80 < (w₂×1) + (w₃×3)
决定性行为	最高评分	100 = (w₁*1）

参数	释义	Thematic CMaps	MovieLens-100K/ MovieLens-1M	MovieLens-10M	MovieLens-20M
size	item向量维度	5	20/100	128	250
window	上下文窗口长度	3	3/4	6	8
negative	负采样个数	32	64/64	128	256
sg/hs	训练模式/采样模式	0/0	0/0	0/0	0/0
min_count	item向量最小频次	3	4/5	6	8
iter	训练迭代次数	5	5/50	100	200
alpha	迭代学习率	0.025	0.025	0.050	0.050

模型	Thematic CMaps	MovieLens-100K	MovieLens-1M	MovieLens-10M	MovieLens-20M
LFM	1.338	1.221	1.196	1.169	1.130
Personal Rank	1.324	1.212	1.183	1.176	1.122
Content Based	1.297	1.194	1.087	1.007	0.914
SVD	1.135	0.938	0.906	0.886	0.850
YouTubeNet	1.129	0.923	0.885	0.872	0.831
Item2Vec(霍夫曼)	1.123	0.917	0.881	0.851	0.807
Item2Vec(负采样)	1.118	0.912	0.875	0.835	0.783

模型	10%	30%	50%	70%	90%
SVD	0.904	0.894	0.886	0.878	0.870
Item2Vec(负采样)	0.867	0.854	0.835	0.814	0.787

Personalized Recommendation Method of Thematic Map Products based on Item2Vec with Negative Sampling Optimization

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 27

Related Articles 15

Metrics

Comments

Recommended 0

[1]	CHEN Ang, YANG Xiuchun, XU Bin, JIN Yunxiang, ZHANG Wenbo, GUO Jian, XING Xiaoyu, YANG Dong. Research on Recognition Methods of Elm Sparse Forest based on Object-based Image Analysis and Deep Learning [J]. Journal of Geo-information Science, 2020, 22(9): 1897-1909.
[2]	CUI Cheng, REN Hongyan, ZHAO Lu, ZHUANG Dafang. Street Space Quality Evaluation in Yuexiu District of Guangzhou City based on Multi-feature Fusion of Street View Imagery [J]. Journal of Geo-information Science, 2020, 22(6): 1330-1338.
[3]	GUO Zihui, LIU Wei. Land Type Interpretation Authenticity Check of Vector Patch Supported by Deep Learning and Remote Sensing Image [J]. Journal of Geo-information Science, 2020, 22(10): 2051-2061.
[4]	SONG Guanfu, LU Hao, WANG Chenliang, HU Chenpu, HUANG Kejia. A Tentative Study on System of Software Technology for Artificial Intelligence GIS [J]. Journal of Geo-information Science, 2020, 22(1): 76-87.
[5]	CAI Bowen,WANG Shugen,WANG Lei,SHAO Zhenfeng. Extraction of Urban Impervious Surface from High-Resolution Remote Sensing Imagery based on Deep Learning [J]. Journal of Geo-information Science, 2019, 21(9): 1420-1429.
[6]	Huihui CAI, Wei ZHU, Zixuan LI, Yuanyuan LIU, Longbin LI, Chang LIU. Prediction Method of Tungsten-molybdenum Prospecting Target Area based on Deep Learning [J]. Journal of Geo-information Science, 2019, 21(6): 928-936.
[7]	Ying FANG, Lianfa LI. Spatiotemporal Estimation of High-Accuracy and High-Resolution Meteorological Parameters based on Machine Learning [J]. Journal of Geo-information Science, 2019, 21(6): 799-813.
[8]	Gang ZHANG, Wenbin LIU, Nan ZHANG. Progressive Morphological Filtering Method of Dense Matching Point Cloud based on Region Feature Segmentation [J]. Journal of Geo-information Science, 2019, 21(4): 615-622.
[9]	Yao YAO, Shuliang REN, Junyi WANG, Qingfeng GUAN. Mapping the Fine-Scale Housing Price Distribution by Integrating a Convolutional Neural Network and Random Forest [J]. Journal of Geo-information Science, 2019, 21(2): 168-177.
[10]	Yilan LIU, Xiaoxia HUANG, Hongga LI, Ze LIU, Chong CHENG, Xin'ge WANG. Extraction of Irregular Solid Waste in Rural based on Convolutional Neural Network and Conditional Random Field Method [J]. Journal of Geo-information Science, 2019, 21(2): 259-268.
[11]	LIU Hao, LUO Jiancheng, HUANG Bo, YANG Haiping, HU Xiaodong, XU Nan, XIA Liegang. Building Extraction based on SE-Unet [J]. Journal of Geo-information Science, 2019, 21(11): 1779-1789.
[12]	Liying ZHANG, Tao PEI, Yijin CHEN, Ci SONG, Xiaoqian LIU. A Review of Urban Environmental Assessment based on Street View Images [J]. Journal of Geo-information Science, 2019, 21(1): 46-58.
[13]	LIU Wentao,LI Shihua,QIN Yuchu. Automatic Building Roof Extraction with Fully Convolutional Neural Network [J]. Journal of Geo-information Science, 2018, 20(11): 1562-1570.
[14]	WANG Jinchuan,TAN Xicheng,WANG Zhaohai,ZHONG Yanfei,DONG Huaping,ZHOU Songtao,CHENG Buyi. Faster R-CNN Deep Learning Network Based Object Recognition of Remote Sensing Image [J]. Journal of Geo-information Science, 2018, 20(10): 1500-1508.
[15]	CHEN Gong,LI Qi,JIN Lingyan,LIANG Heming,Hamed Karimian,MO Yuqin. Spatio-temporal Simulation and Prediction of Regional Ecological Security Based on Deep Learning [J]. Journal of Geo-information Science, 2017, 19(7): 915-923.