在线评论是如何影响APP绩效的——基于情感分析的视角

随着移动互联网的迅猛发展，移动端应用程序（App）也成为人们日常生活中不可分割的一部分。应用商店（APP Store）作为人们下载安装App的主要途径，仅靠其中由开发者所提供的页面图片和描述文本难以使用户充分了解应用的相关信息，而应用商店中包含着的数以亿计的用户评论成为了解APP的另一途径。与评分相比，评论的情绪传达了更丰富的应用信息，已有研究大多基于评论情感的极性（积极、消极）进行分析，但由于情感的多样性和复杂性，仅依靠极性难以对情感进行细致的刻画，本文通过分析情感强度和离散情感，对在线评论的消费者情感进行进一步刻画，研究其对App绩效的影响，并探讨了App更新的中介作用。

本文利用长短期记忆神经网络模型（Long Short-Term Memory, LSTM）对在线评论进行情感分析，识别其情感极性和情感分类，利用词频统计法计算评论的情感强度，构建面板数据并使用双向固定效应模型进行实证分析。研究发现好评占比对App绩效有负面影响，但这种负面影响会随着差评占比的增加而减弱，而差评占比对App绩效呈倒“U”型关系。差评又根据情感强度的不同划分为强烈差评、中等差评和弱差评，研究结果发现3者的占比均对App绩效有显著影响，且强烈差评对App绩效的影响最大。按照情感分类对“失望”和“愤怒”情感的占比进行分析，研究结果发现均对App绩效有显著影响。本文的实证结果还发现，App版本更新在强烈差评占比对App绩效的影响中起到遮掩作用。

[1]Godes D., Mayzlin D., Chen Y., et al. The Firm's Management of Social Interactions. Marketing Letters, 2005, 16(3): 415-428.
[2]Christian Derbaix,Joëlle Vanhamme. Inducing word-of-mouth by eliciting surprise – a pilot investigation[J]. Journal of Economic Psychology,2003,24(1).
[3]Dellarocas C.. The Digitization of Word of Mouth: Promise and Challenges of Online Feedback Mechanisms. Management Science, 2003, 49(10): 1407-1424.
[4]李实,叶强,李一军,Rob Law.中文网络客户评论的产品特征挖掘方法研究[J].管理科学学报,2009,12(02):142-152.
[5]Salovey P, Mayer J D. Emotional intelligence[J]. Imagination, cognition and personality, 1990, 9(3): 185-211.
[6]Amir Gandomi,Murtaza Haider. Beyond the hype: Big data concepts, methods, and analytics[J]. International Journal of Information Management,2015,35(2).
[7]Hu M, Liu B. Mining opinion features in customer reviews[C]//AAAI. 2004, 4(4): 755-760.
[8]Kumar Ravi,Vadlamani Ravi. A survey on opinion mining and sentiment analysis: Tasks, approaches and applications[J]. Knowledge-Based Systems,2015,89.
[9]Liu B. Sentiment analysis: A multi-faceted problem[J]. IEEE Intelligent Systems, 2010, 25(3): 76-80.
[10]王伟, 王洪伟, 盛小宝, 等. 中文在线评论的产品特征与观点识别: 跨领域的比较研究[J]. 管理工程学报, 2017, 31(4): 52-62.
[11]Zhuang L, Jing F, Zhu X Y. Movie review mining and summarization[C]//Proceedings of the 15th ACM international conference on Information and knowledge management. 2006: 43-50.
[12]Hai Z, Chang K, Kim J J, et al. Identifying features in opinion mining via intrinsic and extrinsic domain relevance[J]. IEEE Transactions on Knowledge and Data Engineering, 2013, 26(3): 623-634.
[13]Papadimitriou C H, Raghavan P, Tamaki H, et al. Latent semantic indexing: A probabilistic analysis[J]. Journal of Computer and System Sciences, 2000, 61(2): 217-235.
[14]Blei D M, Ng A Y, Jordan M I. Latent dirichlet allocation[J]. the Journal of machine Learning research, 2003, 3: 993-1022.
[15]Murphy K P. Machine learning: a probabilistic perspective[M]. MIT press, 2012.
[16]Vapnik V. The nature of statistical learning theory[M]. Springer science & business media, 2013.
[17]Li J, Chen Y, Shen Y, et al. Measuring China's Stock Market Sentiment[J]. Available at SSRN 3377684, 2019.
[18]Rozi M F, Mukhlash I, Kimura M. Opinion mining on book review using CNN-L2-SVM algorithm[C]//Journal of Physics: Conference Series. IOP Publishing, 2018, 974(1): 012004.
[19]Wilson T, Wiebe J, Hoffmann P. Recognizing contextual polarity in phrase-level sentiment analysis[C]//Proceedings of human language technology conference and conference on empirical methods in natural language processing. 2005: 347-354.
[20]Hatzivassiloglou V, McKeown K. Predicting the semantic orientation of adjectives[C]//35th annual meeting of the association for computational linguistics and 8th conference of the european chapter of the association for computational linguistics. 1997: 174-181.
[21]Wiebe J. Learning subjective adjectives from corpora[J]. Aaai/iaai, 2000, 20(0): 0.
[22]Ghose A, Ipeirotis P, Sundararajan A. Opinion mining using econometrics: A case study on reputation systems[C]//Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics. 2007: 416-423.
[23]Mihalcea R, Banea C, Wiebe J. Learning multilingual subjective language via cross-lingual projections[C]//Proceedings of the 45th annual meeting of the association of computational linguistics. 2007: 976-983.
[24]Manning C D, Surdeanu M, Bauer J, et al. The Stanford CoreNLP natural language processing toolkit[C]//Proceedings of 52nd annual meeting of the association for computational linguistics: system demonstrations. 2014: 55-60.
[25]Baumeister R F, Vohs K D, Nathan DeWall C, et al. How emotion shapes behavior: Feedback, anticipation, and reflection, rather than direct causation[J]. Personality and social psychology review, 2007, 11(2): 167-203.
[26]刘挺,车万翔,李正华.语言技术平台[J].中文信息学报,2011,25(06):53-62.
[27]Salovey P, Mayer J D. Emotional intelligence[J]. Imagination, cognition and personality, 1990, 9(3): 185-211.
[28]Plutchik R. A general psychoevolutionary theory of emotion[M]//Theories of emotion. Academic press, 1980: 3-33.
[29]Kalat J, Shiota M. Emotion[M]. Nelson Education, 2011.
[30]Wundt W M. Grundriss der psychologie[M]. A. Kröner, 1913.
[31]Mehrabian A, Russell J A. An approach to environmental psychology[M]. the MIT Press, 1974.
[32]Ekman P. An argument for basic emotions[J]. Cognition & emotion, 1992, 6(3-4): 169-200.
[33]Ekman P, Keltner D. Universal facial expressions of emotion[J]. Segerstrale U, P. Molnar P, eds. Nonverbal communication: Where nature meets culture, 1997, 27: 46.
[34]Mudambi S M, Schuff D. Research note: What makes a helpful online review? A study of customer reviews on Amazon. com[J]. MIS quarterly, 2010: 185-200.
[35]Yin D, Bond S D, Zhang H. Anxious or angry? Effects of discrete emotions on the perceived helpfulness of online reviews[J]. MIS quarterly, 2014, 38(2): 539-560.
[36]Yang X, Zhang Z, Zhang Z, et al. Automatic construction and global optimization of a multisentiment lexicon[J]. Computational intelligence and neuroscience, 2016, 2016.
[37]刘丽娜,齐佳音,齐宏伟,蒋思.在线评论中离散情感的分布研究[J].情报科学,2017,35(08):121-128.DOI:10.13833/j.cnki.is.2017.08.054.
[38]Judith A. Chevalier,Dina Mayzlin. The Effect of Word of Mouth on Sales: Online Book Reviews[J]. Journal of Marketing Research,2006,43(3).
[39]Eric K. Clemons,Guodong Gordon Gao,Lorin M. Hitt. When Online Reviews Meet Hyperdifferentiation: A Study of the Craft Beer Industry[J]. Journal of Management Information Systems,2006,23(2).
[40]Pradeep K. Chintagunta,Shyam Gopinath,Sriram Venkataraman. The Effects of Online User Reviews on Movie Box Office Performance: Accounting for Sequential Rollout and Aggregation Across Local Markets[J]. Marketing Science,2010,29(5).
[41]马向阳,徐富明,吴修良,潘靖,李甜.说服效应的理论模型、影响因素与应对策略[J].心理科学进展,2012,20(05):735-744.
[42]Liu Y. Word of mouth for movies: Its dynamics and impact on box office revenue[J]. Journal of marketing, 2006, 70(3): 74-89.
[43]Wenjing Duan,Bin Gu,Andrew B. Whinston. Do online reviews matter? — An empirical investigation of panel data[J]. Decision Support Systems,2008,45(4):
[44]Sun M. How does the variance of product ratings matter?[J]. Management Science, 2012, 58(4): 696-707.
[45]Skowronski John J.,Carlston Donal E.. Negativity and extremity biases in impression formation: A review of explanations.[J]. Psychological Bulletin,1989,105(1).
[46]Cheema A, Papatla P. Relative importance of online versus offline information for Internet purchases: Product category and Internet experience effects[J]. Journal of Business Research, 2010, 63(9-10): 979-985.
[47]Shahana Sen,Dawn Lerman. Why are you telling me this? An examination into negative consumer reviews on the Web[J]. John Wiley & Sons, Ltd,2007,21(4).
[48]Siering M, Muntermann J, Rajagopalan B. Explaining and predicting online review helpfulness: The role of content and reviewer-related signals[J]. Decision Support Systems, 2018, 108: 1-12.
[49]Zhu Feng,Zhang Xiaoquan (Michael). Impact of Online Consumer Reviews on Sales: The Moderating Role of Product and Consumer Characteristics[J]. Journal of Marketing,2010,74(2).
[50]Chen M, Liu X. Predicting popularity of online distributed applications: iTunes app store case analysis[M]//Proceedings of the 2011 iConference. 2011: 661-663.
[51]Picoto W N, Duarte R, Pinto I. Uncovering top-ranking factors for mobile apps through a multimethod approach[J]. Journal of Business Research, 2019, 101: 668-674.
[52]Harman M, Jia Y, Zhang Y. App store mining and analysis: MSR for app stores[C]//2012 9th IEEE working conference on mining software repositories (MSR). IEEE, 2012: 108-111.
[53]陈爽英,雷波,傅锋,李启月.在线评分、APP迭代速度与绩效：平台系统更新的调节效应[J].技术经济,2021,40(10):173-183.
[54]Zhou S, Qiao Z, Du Q, et al. Measuring customer agility from online reviews using big data text analytics[J]. Journal of Management Information Systems, 2018, 35(2): 510-539.
[55]沈艳,陈赟,黄卓.文本大数据分析在经济学和金融学中的应用:一个文献综述[J].经济学(季刊),2019,18(04):1153-1186.
[56]Hsu C L, Lin J C C. Effect of perceived value and social influences on mobile app stickiness and in-app purchase intention[J]. Technological Forecasting and Social Change, 2016, 108: 42-53.
[57]苏婉,李阳春,王天东,郝森森.用户赋能和服务创新对APP绩效的影响研究[J].科研管理,2020,41(08):193-201.DOI:10.19571/j.cnki.1000-2995.2020.08.020.
[58]Boyd D E, Kannan P K, Slotegraaf R J. Branded apps and their impact on firm value: A design perspective[J]. Journal of Marketing Research, 2019, 56(1): 76-88.
[59]Jiang W, Ruan H, Zhang L, et al. For user-driven software evolution: requirements elicitation derived from mining online reviews[C]//Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2014: 584-595.
[60]Lu Z, Yang D, Li J. A software evaluation system based on reviews mining[J]. Computer Applications and Software, 2014, 31(7): 1-4.
[61]Syer M D, Nagappan M, Hassan A E, et al. Revisiting prior empirical findings for mobile apps: An empirical case study on the 15 most popular open-source Android apps[C]//Proceedings of the 2013 Conference of the Center for Advanced Studies on Collaborative Research. 2013: 283-297.
[62]Iacob C, Harrison R, Faily S. Online reviews as first class artifacts in mobile app development[C]//International Conference on Mobile Computing, Applications, and Services. Springer, Cham, 2013: 47-53.
[63]Sherwin Rosen. Hedonic Prices and Implicit Markets: Product Differentiation in Pure Competition[J]. Sherwin Rosen,1974,82(1).
[64]Panichella S, Di Sorbo A, Guzman E, et al. How can i improve my app? classifying user reviews for software maintenance and evolution[C]//2015 IEEE international conference on software maintenance and evolution (ICSME). IEEE, 2015: 281-290.
[65]Khalid H, Shihab E, Nagappan M, et al. What do mobile app users complain about?[J]. IEEE software, 2014, 32(3): 70-77.
[66]Guzman E, El-Haliby M, Bruegge B. Ensemble methods for app review classification: An approach for software evolution (n)[C]//2015 30th IEEE/ACM International Conference on Automated Software Engineering (ASE). IEEE, 2015: 771-776.
[67]钱宇,曹恩叶,邓文君,等. 海量用户评论在APP更新设计中的参与作用挖掘[J]. 系统工程理论与实践,2021,41(3):554-564. DOI:10.12011/SETP2019-1136.
[68]Menguc B, Auh S, Yannopoulos P. Customer and supplier involvement in design: The moderating role of incremental and radical innovation capability[J]. Journal of Product Innovation Management, 2014, 31(2): 313-328.
[69]Foglieni F, Holmlid S. Determining service value: Exploring the link between value creation and service evaluation[J]. Service Science, 2017, 9(1): 74-90.
[70]Ye H J, Kankanhalli A. Value cocreation for service innovation: Examining the relationships between service innovativeness, customer participation, and mobile app performance[J]. Journal of the Association for Information Systems, 2020, 21(2): 8.
[71]Nikolay Archak,Anindya Ghose,Panagiotis G. Ipeirotis. Deriving the Pricing Power of Product Features by Mining Consumer Reviews[J]. Management Science,2011,57(8).
[72]俞一凡. 在线评论中的离散情绪对销售的预测作用[D]. 清华大学, 2018.
[73]Quan C, Ren F. A blog emotion corpus for emotional expression analysis in Chinese[J]. Computer Speech & Language, 2010, 24(4): 726-749.
[74]鞠天骄. 在线评论对移动应用下载影响的实证研究[D].吉林大学,2017.
[75]祝琳琳. 在线评论信息质量感知研究[D].吉林大学,2020.DOI:10.27162/d.cnki.gjlin.2020.001230.
[76]陈平平,耿笑冉,邹敏,谭定英.基于机器学习的文本情感倾向性分析[J].计算机与现代化,2020(03):77-81+92.
[77]Goodfellow I, Bengio Y, Courville A. Deep learning[M]. MIT press, 2016.
[78]Jason W. Wei,Kai Zou. EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks.[J]. CoRR,2019,abs/1901.11196:
[79]Turney P D. Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews[J]. arXiv preprint cs/0212032, 2002.
[80]秦赏. 现代汉语程度副词表量研究[D].河北大学,2018.
[81]王洪伟,宋媛,杜战其,郑丽娟,华瑾,张艺伟.基于在线评论情感分析的快递服务质量评价[J].北京工业大学学报,2017,43(03):402-412.
[82]黄敏学,郑仕勇,王琦缘.网络关系与口碑“爆点”识别——基于社会影响理论的实证研究[J].南开管理评论,2019,22(02):45-60.
[83]Wenjing Duan,Bin Gu,Andrew B. Whinston. The dynamics of online word-of-mouth and product sales—An empirical investigation of the movie industry[J]. Journal of Retailing,2008,84(2).
[84]Ghose A, Ipeirotis P G. Designing ranking systems for consumer reviews: The impact of review subjectivity on product sales and review quality[C]//Proceedings of the 16th annual workshop on information technology and systems. 2006, 303(10).
[85]Weinburger M C, Dillon W R, Olson J. The effects of unfavorable product information[J]. Advances in consumer research, 1980, 7: 528-532.
[86]Skowronski John J.,Carlston Donal E.. Negativity and extremity biases in impression formation: A review of explanations.[J]. Psychological Bulletin,1989,105(1).
[87]Baumeister R F, Bratslavsky E, Finkenauer C, et al. Bad is stronger than good[J]. Review of general psychology, 2001, 5(4): 323-370.
[88]Rohini Ahluwalia,Robert E. Burnkrant,H. Rao Unnava. Consumer Response to Negative Publicity: The Moderating Role of Commitment[J]. Journal of Marketing Research,2000,37(2).
[89]Phillip Nelson. Information and Consumer Behavior[J]. Phillip Nelson,1970,78(2).
[90]Rashmi Adaval. Sometimes It Just Feels Right: The Differential Weighting of Affect‐Consistent and Affect‐Inconsistent Product Information[J]. Journal of Consumer Research,2001,28(1).
[91]郝媛媛,邹鹏,李一军,叶强.基于电影面板数据的在线评论情感倾向对销售收入影响的实证研究[J].管理评论,2009,21(10):95-103.
[92]Golmohammadi A, Mattila A S, Gauri D K. Negative online reviews and consumers’ service consumption[J]. Journal of Business Research, 2020, 116: 27-36.
[93]Shahana Sen,Dawn Lerman. Why are you telling me this? An examination into negative consumer reviews on the Web[J]. Journal of Interactive Marketing,2007,21(4).
[94]Pham M T. Representativeness, relevance, and the use of feelings in decision making[J]. Journal of consumer research, 1998, 25(2): 144-159.
[95]Batra R, Ahtola O T. Measuring the hedonic and utilitarian sources of consumer attitudes[J]. Marketing letters, 1991, 2(2): 159-170.
[96]Mort G S, Rose T. The effect of product type on value linkages in the means‐end chain: implications for theory and method[J]. Journal of Consumer Behaviour: An International Research Review, 2004, 3(3): 221-234.
[97]Higgins E T. Beyond pleasure and pain[J]. American psychologist, 1997, 52(12): 1280.
[98]Merton R K. The Matthew effect in science: The reward and communication systems of science are considered[J]. Science, 1968, 159(3810): 56-63.
[99]Zhang L, Wei W, Line N D, et al. When positive reviews backfire: The effect of review dispersion and expectation disconfirmation on Airbnb guests’ experiences[J]. International Journal of Hospitality Management, 2021, 96: 102979.
[100]Zhao X, Gu B, Whinston A. The influence of online word-of-mouth long tail formation: an empirical analysis[C]//Proceedings of the Conference on Information Systems and Technology (CIST 2008). 2008: 11-12.
[101]Anderson C. The long tail: Why the future of business is selling less of more[M]. Hachette Books, 2006.
[102]Brynjolfsson E, Hu Y, Simester D. Goodbye pareto principle, hello long tail: The effect of search costs on the concentration of product sales[J]. Management Science, 2011, 57(8): 1373-1386.
[103]Cao Q, Duan W, Gan Q. Exploring determinants of voting for the “helpfulness” of online user reviews: A text mining approach[J]. Decision Support Systems, 2011, 50(2): 511-521.
[104]Korfiatis N, García-Bariocanal E, Sánchez-Alonso S. Evaluating content quality and helpfulness of online product reviews: The interplay of review helpfulness vs. review content[J]. Electronic Commerce Research and Applications, 2012, 11(3): 205-217.
[105]Lee S, Choeh J Y. Predicting the helpfulness of online reviews using multilayer perceptron neural networks[J]. Expert Systems with Applications, 2014, 41(6): 3041-3046.
[106]Smith C A, Lazarus R S. Emotion and adaptation[J]. Handbook of personality: Theory and research, 1990, 21: 609-637.
[107]Han S, Lerner J S, Keltner D. Feelings and consumer decision making: The appraisal‐tendency framework[J]. Journal of consumer psychology, 2007, 17(3): 158-168.
[108]Lerner J S, Keltner D. Beyond valence: Toward a model of emotion-specific influences on judgement and choice[J]. Cognition & emotion, 2000, 14(4): 473-493.
[109]Raghunathan R, Pham M T. All negative moods are not equal: Motivational influences of anxiety and sadness on decision making[J]. Organizational behavior and human decision processes, 1999, 79(1): 56-77.
[110]Bond S D, He S X, Wen W. Speaking for “free”: Word of mouth in free-and paid-product settings[J]. Journal of Marketing Research, 2019, 56(2): 276-290.
[111]Erik Brynjolfsson,Yu (Jeffrey) Hu,Michael D. Smith. Consumer Surplus in the Digital Economy: Estimating the Value of Increased Product Variety at Online Booksellers[J]. Management Science,2003,49(11).
[112]Anindya Ghose,Arun Sundararajan. Evaluating Pricing Strategy Using e-Commerce Data: Evidence and Estimation Challenges[J]. Statistical Science,2006,21(2).
[113]Judith Chevalier,Austan Goolsbee. Measuring Prices and Price Competition Online: Amazon.com and BarnesandNoble.com[J]. Quantitative Marketing and Economics,2003,1(2).
[114]Duan W, Gu B, Whinston A B. Informational cascades and software adoption on the internet: an empirical investigation[J]. MIS quarterly, 2009: 23-48.
[115]情报学报. 情感词汇本体的构造. 2009.温忠麟,叶宝娟.中介效应分析:方法和模型发展[J].心理科学进展,2014,22(05):731-745.