請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/71723
標題: | 使用擴展深度合作神經網路和評論來提升評分預測 Improve Rating Prediction Using Extended Deep Cooperative Neural Network and Reviews |
作者: | Jin-Tao Yu 郁錦濤 |
指導教授: | 廖世偉(Shih-Wei Liao) |
關鍵字: | 推薦系統,神經網路,商品評論,用戶評論,評分預測,隱語義模型,神經協同過濾, Recommender Systems,Neural Network,Item Reviews,User Reviews,Rating Prediction,Latent Factor Model,Neural Collaborative Filtering, |
出版年 : | 2018 |
學位: | 碩士 |
摘要: | 近年來基於矩陣分解技術的協同過濾方法在推薦系統上已經取得了巨大的成功,但是冷開始和數據稀疏這兩個問題並沒有很好的解決。由用戶撰寫的商品評論包含巨量的信息,因此將評論信息引入推薦系統進行評分預測來緩解上述問題已經成一個研究趨勢。在最近的研究當中表明,當存在評論文本時,相比較於傳統方法,深度學習方法能夠提高評分預測的表現。
一個叫深度合作神經網路的模型已經被提出,旨在用評論文本來構建用戶和商品的潛在代表。它包含兩個兩個並行的卷積神經網絡,一個神經網絡利用某個用戶的所有商品評論學習用戶的潛在特徵,另一個神經網路利用某個商品的所有用戶評論學習商品的潛在特徵。最後,將用戶的潛在特徵和商品的潛在特徵通過一個共享層組合起來,作分解機器的輸入。 在這篇論文中,我首先運用tensorflow的工具實現了深度合作神經網路模型。然後,我提出一種方法將深度合作神經網路模型進行擴展,將它的共享層從分解機器變成一個神經預測層。神經預測層是基於神經協同過濾技術。因此,我提出的擴展模型集合了深度學習技術和協同過濾方法。 在實驗中,在Amazon公開數據集中,擴展深度神經網絡模型比原始的深度合作神經網絡模型表現好。 In recent years, collaborative filtering methods based on matrix factorization techniques have achieved great success in recommender systems, while cold-start and data sparsity have not solved well. Item reviews written by users have a large amount of information, hence it has been a significant trend to involve review information into rating prediction as one of the dominant solutions. In recent research, it has been shown that deep learning methods can improve the performance of rating prediction over traditional methods when review text is available. A model named Deep Cooperative Neural Networks (DeepCoNN) has been pro-posed, which aims to build user and item latent representations using review text. It consists of two parallel convolution neural networks, where one neural network learns user latent features using the reviews written by the user, and the other neu-ral network learns item latent features using the reviews for the item. Finally, a shared layer combines user representations and item representations as the input of factorization machines. In this thesis, I first implement the DeepCoNN model by tensorflow tools. Then I propose an idea that I extend DeepCoNN by changing its shared layer from factor-ization machines to a neural prediction layer. The neural prediction layer is based on neural collaborative filtering techniques. Hence the extended model I proposed combines deep learning and collaborative filtering. In the experiments, the extended DeepCoNN model outperforms the original DeepCoNN model in Amazon public datasets. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/71723 |
DOI: | 10.6342/NTU201801314 |
全文授權: | 有償授權 |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-107-1.pdf 目前未授權公開取用 | 1.03 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。