利用深度學習演算法分析商品描述自動擴增電子商務產品階層

Constructing Hierarchical Product Categories for E-commerce by Word Embedding and Clustering

謝怡翔(YI-HSAING HSIEH)

指導教授 ： 吳世弘

朝陽科技大學/資訊學院/資訊工程系/碩士(2017年)

摘要

本論文目標在於分析電子商務中不同產品分類的階層，特別像是淘寶網、京東購物或亞馬遜書店上的產品。不同的電子商務網站販售類似的產品，但是由於分類的方式不同，難以整合比較。目前遇到的問題一：商品分類階層較淺，過多產品分在同一類，無法區分性質上的差異。眾多商品分在同一類，從而使消費者難以選擇。問題二：商品分類階層為人工編輯，大量新商品加入時難以維護。本論文將以淘寶網等電子商務網站的產品說明為語料，利用深度學習分析網站上的文字，找出各種產品階層化的關聯性。研究中將利用機器學習的分群演算法，自動產生階層化的分類。其中關於產品的關連度將利用深度學習演算法，自動分析產品文本的相似性。研究結果將可以更清楚區分眾多產品的類型，產生有用的階層化分類。階層化分類將有助於相關業者配送，以及消費者購物時縮小選擇空間方便購物。

關鍵字

商品階層 ； 電子商務 ； 聚類演算法 ； 詞嵌入 ； 商品描述分析

並列摘要

The objective of the study is to generate the product hierarchical categories in e-commerce, particularly for e-commerce giants such as Taobao or Jingdong. For e-commerce websites the amount of products is huge, and a hierarchical structure is necessary for consumers to browse them. We find that there are two problems in the current websites: firstly, the hierarchy is shallow; there are often too many products in the same category, it is hard for a consumer browse them. Secondly, the hierarchy is constructed manually, when new products come, it is hard to update the hierarchy. Based on the product description analysis, it is possible to solve the problems. In this study, we will use the deep learning word embedding technology and clustering algorithm to construct a deeper product hierarchy automatically. The results will help the customers to choose products with a more clear structure and also help the e-commerce company to save the maintaining effort on the product hierarchy.

並列關鍵字

Product description analysis ； Product hierarchy ； E-commerce ； Clustering algorithm ； Word embedding

參考文獻

[1] e eMarketer Jul. 2014, http://www.emarketer.com

[2] 資策會FIND「臺灣消費者雙十一線上購物行為」Nov. 2015

[3] Q. Le and T. Mikolov: Distributed representations of sentences and documents. In Proceedings of the 31st International Conference on Machine Learning (ICML-14), 2014.(sent2vec)

[4] T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean: Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems, pages 3111--3119, 2013.

[5] Deng, L.; Yu, D. (2014): Deep Learning: Methods and Applications" (PDF. Foundations and Trends in Signal Processing 7: 3–4. Doi:10.1561/2000000039.