Review-Based Tip Generation for Music Songs

Reviews of songs play an important role in online music service platforms. Prior research shows that users can make quicker and more informed decisions when presented with meaningful song reviews. However, reviews of music songs are generally long in length and most of them are non-informative for users. It is difficult for users to efficiently grasp meaningful messages for making decisions. To solve this problem, one practical strategy is to provide tips , i.e., short, concise, empathetic, and self- contained descriptions about songs. Tips are produced from song reviews and should express non-trivial insight about the songs. To the best of our knowledge, no prior studies have explored the tip generation task in music domain. In this paper, we create a dataset named MTips for the task and propose a framework named G EN TMS for automatically generating tips from song reviews. The dataset involves 8,003 Chinese tips/non-tips from 128 songs which are distributed in five different song genres. Experimental results show that G EN TMS achieves top-10 precision at 85.56%, outperforming the baselinemodelsbyatleast3.34%. Besides, tosimulatethepracticalusageofourproposedframework, we also experiment with previously-unseen songs, during which G EN TMS also achieves the best per- formance with top-10 precision at 78.89% on average. The results demonstrate the effectiveness of the proposed framework in tip generation of the music domain.

[1]  Eugene Agichtein,et al.  Identifying Helpful Sentences in Product Reviews , 2021, NAACL.

[2]  Slava Novgorodov,et al.  Generating Tips from Product Reviews , 2021, WSDM.

[3]  Furu Wei,et al.  At Which Level Should We Extract? An Empirical Analysis on Extractive Document Summarization , 2020, COLING.

[4]  Ruifeng Yuan,et al.  Fact-level Extractive Summarization with Hierarchical Graph Mask on BERT , 2020, COLING.

[5]  Quan Z. Sheng,et al.  Multi-document Summarization via Deep Learning Techniques: A Survey , 2020, ACM Comput. Surv..

[6]  Fuzheng Zhang,et al.  Query-aware Tip Generation for Vertical Search , 2020, International Conference on Information and Knowledge Management.

[7]  Jed R. Brubaker,et al.  P4KxSpotify: A Dataset of Pitchfork Music Reviews and Spotify Musical Features , 2020, ICWSM.

[8]  Pengfei Liu,et al.  Heterogeneous Graph Neural Networks for Extractive Document Summarization , 2020, ACL.

[9]  Yu Cheng,et al.  Discourse-Aware Neural Extractive Text Summarization , 2019, ACL.

[10]  Mirella Lapata,et al.  Text Summarization with Pretrained Encoders , 2019, EMNLP.

[11]  Hassan Foroosh,et al.  Improving the Similarity Measure of Determinantal Point Processes for Extractive Multi-Document Summarization , 2019, ACL.

[12]  Ido Guy,et al.  Generating Product Descriptions from User Reviews , 2019, WWW.

[13]  Piji Li,et al.  Persona-Aware Tips Generation? , 2019, WWW.

[14]  Xiaoyong Du,et al.  Analogical Reasoning on Chinese Morphological and Semantic Relations , 2018, ACL.

[15]  Theodoros Lappas,et al.  Unsupervised tip-mining from customer reviews , 2018, Decis. Support Syst..

[16]  Frank Hutter,et al.  Fixing Weight Decay Regularization in Adam , 2017, ArXiv.

[17]  Laming Chen,et al.  Fast Greedy MAP Inference for Determinantal Point Process to Improve Recommendation Diversity , 2017, NeurIPS.

[18]  Piji Li,et al.  Neural Rating Regression with Abstractive Tips Generation for Recommendation , 2017, SIGIR.

[19]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[20]  Ido Guy,et al.  Extracting and Ranking Travel Tips from User-Generated Reviews , 2017, WWW.

[21]  Xavier Serra,et al.  Exploring Customer Reviews for Music Genre Classification and Evolutionary Studies , 2016, ISMIR.

[22]  Tomas Mikolov,et al.  Bag of Tricks for Efficient Text Classification , 2016, EACL.

[23]  Diyi Yang,et al.  Hierarchical Attention Networks for Document Classification , 2016, NAACL.

[24]  Jianfeng Gao,et al.  A Diversity-Promoting Objective Function for Neural Conversation Models , 2015, NAACL.

[25]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[26]  Ben Taskar,et al.  Determinantal Point Processes for Machine Learning , 2012, Found. Trends Mach. Learn..

[27]  Barbara Di Eugenio,et al.  Generating Fine-Grained Reviews of Songs from Album Reviews , 2010, ACL.

[28]  Andreas F. Ehmann,et al.  Mining Music Reviews: Promising Preliminary Results , 2005, ISMIR.

[29]  Rada Mihalcea,et al.  TextRank: Bringing Order into Text , 2004, EMNLP.

[30]  Thomas Hofmann,et al.  Probabilistic Latent Semantic Analysis , 1999, UAI.

[31]  Thorsten Joachims,et al.  Text Categorization with Support Vector Machines: Learning with Many Relevant Features , 1998, ECML.

[32]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.