隨著行動應用程式的數量急遽成長，琳琅滿目的行動應用程式使得用戶要找到適合的選擇是困難且費時的。因此，幫助用戶解決此問題的行動應用程式推薦成為當務之急。過去研究解決此一問題常見的兩種做法，一種是對評分資料實施矩陣分解，以預測目標用戶對其他應用程式的可能評分。第二種做法則是根據用戶評論文本去預測評分。
　　本研究除了結合以上兩種傳統的作法外，更結合了深度學習的模式以產生更佳的模型。對於評分數據，我們採用深度矩陣分解來取得對應嵌入，以此增進用戶與項目的向量表示；對於評論文本，我們結合了多種嵌入方法所生成的表示以豐富輸入資訊，也更進一步提升評論文本所帶來的優勢。此外，我們的方法也結合了具備非線性轉換能力的深度神經網路，以提取更具代表性的抽象特徵。
　　我們透過蒐集自真實世界的數據集進行實驗，大量的實驗結果表明，我們提出的方法性能優於其他基線方法。另外，我們透過廣泛的實驗評估不同實驗設置的性能，同時也證明了我們所使用的多嵌入方法可以提供更好的推薦性能。

With the explosion in the number of mobile applications, it becomes difficult and time-consuming for users to find the most suitable and interesting apps from the millions of applications that exist today. Therefore, mobile application recommendation has become an immediate priority to help people address this problem. There are two common approaches to this question in previous studies, one is applying matrix factorization to the rating data to predict ratings of other applications by the target users. Another approach is to predict ratings based on users’ reviewing text. In addition to combining the above two traditional approaches, this study also incorporates deep learning methods to generate better models. For rating data, we use the deep matrix factorization method to obtain the latent factor vectors of users and items from the rating matrix as the input of the rating learning module to improve the representation of the rating. For the review text, we improved the text representation by using a multi-embedding approach. On top of that, our model also combines with the deep neural network which has the nonlinear transformation ability to extract more representative abstract features. We conduct experiments on the dataset which is collected from the real world. A large number of experimental results show that our proposed method has better performance than other existing methods. In addition, we evaluate the performance of different experimental setups through extensive experiments and proves that the multi-embedding approach we used can improve recommendation performance.

[1] J. L. Herlocker, J. A. Konstan, L. G. Terveen, and J. T. Riedl, “Evaluating collaborative filtering recommender systems,” ACM Trans. Inf. Syst., vol. 22, no. 1, pp. 5–53, Jan. 2004, doi: 10.1145/963770.963772.
[2] G. Adomavicius and A. Tuzhilin, “Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions,” IEEE Trans. Knowl. Data Eng., vol. 17, no. 6, pp. 734–749, Jun. 2005, doi: 10.1109/TKDE.2005.99.
[3] A. Boutet, D. Frey, R. Guerraoui, A. Jégou, and A.-M. Kermarrec, “WHATSUP: A Decentralized Instant News Recommender,” in 2013 IEEE 27th International Symposium on Parallel and Distributed Processing, May 2013, pp. 741–752. doi: 10.1109/IPDPS.2013.47.
[4] A. Karatzoglou, L. Baltrunas, K. Church, and M. Böhmer, Climbing the app wall: Enabling mobile app discovery through context-aware recommendations. 2012, p. 2530. doi: 10.1145/2396761.2398683.
[5] S. Rendle, C. Freudenthaler, Z. Gantner, and L. Schmidt-Thieme, “BPR: Bayesian Personalized Ranking from Implicit Feedback,” p. 10, 2009.
[6] B. Sarwar, G. Karypis, J. Konstan, and J. Riedl, “Item-based collaborative filtering recommendation algorithms,” in Proceedings of the 10th international conference on World Wide Web, New York, NY, USA, Apr. 2001, pp. 285–295. doi: 10.1145/371920.372071.
[7] K. Shi and K. Ali, “GetJar mobile application recommendations with very sparse datasets,” in Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD ’12, Beijing, China, 2012, p. 204. doi: 10.1145/2339530.2339563.
[8] D. Liu and W. Jiang, “Personalized App Recommendation Based on Hierarchical Embedding,” in 2018 IEEE SmartWorld, Ubiquitous Intelligence Computing, Advanced Trusted Computing, Scalable Computing Communications, Cloud Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI), Oct. 2018, pp. 1323–1328. doi: 10.1109/SmartWorld.2018.00230.
[9] H. Yu, X. Xia, X. Zhao, and W. Qiu, “Combining Collaborative Filtering and Topic Modeling for More Accurate Android Mobile App Library Recommendation,” in Proceedings of the 9th Asia-Pacific Symposium on Internetware, New York, NY, USA, Sep. 2017, pp. 1–6. doi: 10.1145/3131704.3131721.
[10] X. Wu and Y. Zhu, “A Hybrid Approach Based on Collaborative Filtering to Recommending Mobile Apps,” in 2016 IEEE 22nd International Conference on Parallel and Distributed Systems (ICPADS), Dec. 2016, pp. 8–15. doi: 10.1109/ICPADS.2016.0011.
[11] W. Woerndl, C. Schueller, and R. Wojtech, “A Hybrid Recommender System for Context-aware Recommendations of Mobile Applications,” in 2007 IEEE 23rd International Conference on Data Engineering Workshop, Apr. 2007, pp. 871–878. doi: 10.1109/ICDEW.2007.4401078.
[12] E. Costa-Montenegro, A. B. Barragáns-Martínez, and M. Rey-López, “Which App? A recommender system of applications in markets: Implementation of the service for monitoring users’ interaction,” Expert Syst. Appl., vol. 39, no. 10, pp. 9367–9375, Aug. 2012, doi: 10.1016/j.eswa.2012.02.131.
[13] G. Ling, M. Lyu, and I. King, “Ratings meet reviews, a combined approach to recommend,” RecSys 2014 - Proc. 8th ACM Conf. Recomm. Syst., pp. 105–112, Oct. 2014, doi: 10.1145/2645710.2645728.
[14] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA, USA: MIT Press, 2016.
[15] C. Guo, Y. Xu, X. Hou, N. Dong, J. Xu, and Q. Ye, “Deep Attentive Factorization Machine for App Recommendation Service,” in 2019 IEEE International Conference on Web Services (ICWS), Jul. 2019, pp. 134–138. doi: 10.1109/ICWS.2019.00032.
[16] K. Niu, H. Jiao, X. Xu, C. Cheng, and C. Wang, “A Novel Learning Approach to Improve Mobile Application Recommendation Diversity,” in 2018 IEEE International Conference on Data Mining Workshops (ICDMW), Nov. 2018, pp. 1300–1307. doi: 10.1109/ICDMW.2018.00185.
[17] H.-T. Cheng et al., “Wide & Deep Learning for Recommender Systems,” ArXiv160607792 Cs Stat, Jun. 2016, Accessed: Mar. 15, 2022. [Online]. Available: http://arxiv.org/abs/1606.07792
[18] P. Li, Z. Wang, Z. Ren, L. Bing, and W. Lam, “Neural Rating Regression with Abstractive Tips Generation for Recommendation,” Proc. 40th Int. ACM SIGIR Conf. Res. Dev. Inf. Retr., pp. 345–354, Aug. 2017, doi: 10.1145/3077136.3080822.
[19] M. U. Khan, R. M. U. Khalid, S. A. Burhan, and M. Nauman, “Machine Learning Based Recommendation System For Android Apps,” in 2021 13th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Jul. 2021, pp. 1–4. doi: 10.1109/ECAI52376.2021.9515087.
[20] T. Mikolov, I. Sutskever, K. Chen, G. s Corrado, and J. Dean, “Distributed Representations of Words and Phrases and their Compositionality,” Adv. Neural Inf. Process. Syst., vol. 26, Oct. 2013.
[21] J. Pennington, R. Socher, and C. Manning, “GloVe: Global Vectors for Word Representation,” in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, Oct. 2014, pp. 1532–1543. doi: 10.3115/v1/D14-1162.
[22] M. E. Peters et al., “Deep contextualized word representations,” ArXiv180205365 Cs, Mar. 2018, Accessed: Mar. 15, 2022. [Online]. Available: http://arxiv.org/abs/1802.05365
[23] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” ArXiv181004805 Cs, May 2019, Accessed: Mar. 15, 2022. [Online]. Available: http://arxiv.org/abs/1810.04805
[24] W. Yin and H. Schütze, “Learning Word Meta-Embeddings,” in Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Berlin, Germany, Aug. 2016, pp. 1351–1360. doi: 10.18653/v1/P16-1128.
[25] J. Turian, L. Ratinov, and Y. Bengio, “Word representations: a simple and general method for semi-supervised learning,” in Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, USA, Jul. 2010, pp. 384–394.
[26] K. Zhang, Z. Lian, J. Li, H. Li, and X. Hu, “Short Text Clustering with a Deep Multi-embedded Self-supervised Model,” in Artificial Neural Networks and Machine Learning – ICANN 2021, Cham, 2021, pp. 150–161. doi: 10.1007/978-3-030-86383-8_12.
[27] Y. Liu et al., “RoBERTa: A Robustly Optimized BERT Pretraining Approach,” ArXiv190711692 Cs, Jul. 2019, Accessed: Mar. 15, 2022. [Online]. Available: http://arxiv.org/abs/1907.11692
[28] M. Gan, Y. Ma, and K. Xiao, “CDMF: A Deep Learning Model based on Convolutional and Dense-layer Matrix Factorization for Context-Aware Recommendation,” 2019. doi: 10.24251/HICSS.2019.138.
[29] X. He, L. Liao, H. Zhang, L. Nie, X. Hu, and T.-S. Chua, “Neural Collaborative Filtering,” ArXiv170805031 Cs, Aug. 2017, Accessed: Mar. 15, 2022. [Online]. Available: http://arxiv.org/abs/1708.05031
[30] H. Cao, “Mining smartphone data for app usage prediction and recommendations: A survey,” Pervasive Mob. Comput., vol. 37, pp. 1–22, Jan. 2017, doi: 10.1016/j.pmcj.2017.01.007.
[31] Y. Wu et al., “Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation,” ArXiv160908144 Cs, Oct. 2016, Accessed: Mar. 16, 2022. [Online]. Available: http://arxiv.org/abs/1609.08144
[32] H.-J. Xue, X. Dai, J. Zhang, S. Huang, and J. Chen, “Deep Matrix Factorization Models for Recommender Systems,” in Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, Melbourne, Australia, Aug. 2017, pp. 3203–3209. doi: 10.24963/ijcai.2017/447.
[33] L. Zheng, V. Noroozi, and P. S. Yu, “Joint Deep Modeling of Users and Items Using Reviews for Recommendation,” ArXiv170104783 Cs, Jan. 2017, Accessed: Mar. 16, 2022. [Online]. Available: http://arxiv.org/abs/1701.04783
[34] R. Catherine and W. Cohen, “TransNets: Learning to Transform for Recommendation,” Proc. Elev. ACM Conf. Recomm. Syst., pp. 288–296, Aug. 2017, doi: 10.1145/3109859.3109878.
[35] A. Mnih and R. R. Salakhutdinov, “Probabilistic Matrix Factorization,” in Advances in Neural Information Processing Systems, 2007, vol. 20. Accessed: Jun. 28, 2022. [Online]. Available: https://proceedings.neurips.cc/paper/2007/hash/d7322ed717dedf1eb4e6e52a37ea7bcd-Abstract.html
[36] Y. Koren, “Factorization meets the neighborhood: a multifaceted collaborative filtering model,” in Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, New York, NY, USA, Aug. 2008, pp. 426–434. doi: 10.1145/1401890.1401944.
[37] Y. Koren, R. Bell, and C. Volinsky, “Matrix Factorization Techniques for Recommender Systems,” Computer, vol. 42, no. 8, pp. 30–37, Aug. 2009, doi: 10.1109/MC.2009.263.
[38] D. D. Lee and H. S. Seung, “Learning the parts of objects by non-negative matrix factorization,” Nature, vol. 401, no. 6755, Art. no. 6755, Oct. 1999, doi: 10.1038/44565.
[39] G. Chen, F. Wang, and C. Zhang, “Collaborative Filtering Using Orthogonal Nonnegative Matrix Tri-factorization,” in Seventh IEEE International Conference on Data Mining Workshops (ICDMW 2007), Oct. 2007, pp. 303–308. doi: 10.1109/ICDMW.2007.18.
[40] Q. Gu, J. Zhou, and C. Ding, “Collaborative Filtering: Weighted Nonnegative Matrix Factorization Incorporating User and Item Graphs,” Apr. 2010, pp. 199–210. doi: 10.1137/1.9781611972801.18.
[41] C. Chen, M. Zhang, Y. Liu, and S. Ma, “Neural Attentional Rating Regression with Review-level Explanations,” in Proceedings of the 2018 World Wide Web Conference, Republic and Canton of Geneva, CHE, Apr. 2018, pp. 1583–1592. doi: 10.1145/3178876.3186070.
[42] Y. Tay, A. Luu, and S. Hui, “Multi-Pointer Co-Attention Networks for Recommendation,” Jul. 2018, pp. 2309–2318. doi: 10.1145/3219819.3220086.
[43] D. Liu, J. Li, B. Du, J. Chang, and R. Gao, “DAML: Dual Attention Mutual Learning between Ratings and Reviews for Item Recommendation,” in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, New York, NY, USA, Jul. 2019, pp. 344–352. doi: 10.1145/3292500.3330906.
[44] D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” Dec. 2014, doi: 10.48550/arXiv.1412.6980.
[45] A. Vaswani et al., “Attention is All you Need,” in Advances in Neural Information Processing Systems, 2017, vol. 30. Accessed: Jun. 11, 2022. [Online]. Available: https://proceedings.neurips.cc/paper/2017/hash/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html