Abstract
The content and style of the text constitutes the semantic context of its words—a property that is important for many downstream tasks in natural language processing. We demonstrate the advantages of incorporating domain information for affect analysis, and subsequently for the prediction of user responses to marketing emails. Emails are a primary form of marketing communication, and email subject lines are the only indicators of whether the receiver will open an email especially in the case of bulk communication. We analyze the performance of affective features in predicting email opens, on a dataset of 60,000 unique promotion emails from 3 different industries. Our results show that the use of domain-specific affect words is strongly correlated with email opens and outperforms words from the standard ANEW lexicon and other state of the art affective lexica. Implications of this findings can be incorporated into writing tools to improve the productivity of marketing campaigns.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
See http://www.edatasource.com. Edatasource monitors the email inboxes of millions of email users, after obtaining their consent, and saves email contents and user responses in a de-identified form for the purposes of marketing research.
- 2.
References
Bradley, M.M., Lang, P.J.: Affective norms for english words (anew): instruction manual and affective ratings. Technical report, Technical report C-1, the center for research in psychophysiology, University of Florida (1999)
Lim, K.H., Lim, E.P., Jiang, B., Achananuparp, P.: Using online controlled experiments to examine authority effects on user behavior in email campaigns. In: Proceedings of the 27th ACM Conference on Hypertext and Social Media, pp. 255–260. ACM (2016)
Di Castro, D., Karnin, Z., Lewin-Eytan, L., Maarek, Y.: You’ve got mail, and here is what you could do with it!: analyzing and predicting actions on email messages. In: Proceedings of the Ninth ACM International Conference on Web Search and Data Mining, pp. 307–316. ACM (2016)
Sahni, N.S., Wheeler, S.C., Chintagunta, P.K.: Personalization in email marketing: the role of non-informative advertising content (2016)
Luo, X., Nadanasabapathy, R., Zincir-Heywood, A.N., Gallant, K., Peduruge, J.: Predictive analysis on tracking emails for targeted marketing. In: Japkowicz, N., Matwin, S. (eds.) DS 2015. LNCS (LNAI), vol. 9356, pp. 116–130. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24282-8_11
Warriner, A.B., Kuperman, V., Brysbaert, M.: Norms of valence, arousal, and dominance for 13,915 English lemmas. Behav. Res. Methods 45, 1191–1207 (2013)
Taboada, M., Brooke, J., Tofiloski, M., Voll, K., Stede, M.: Lexicon-based methods for sentiment analysis. Comput. Linguist. 37, 267–307 (2011)
Esuli, A., Sebastiani, F.: Sentiwordnet: a publicly available lexical resource for opinion mining. In: Proceedings of LREC, vol. 6, pp. 417–422. Citeseer (2006)
Qiu, G., Liu, B., Bu, J., Chen, C.: Opinion word expansion and target extraction through double propagation. Comput. Linguist. 37, 9–27 (2011)
Blitzer, J., Dredze, M., Pereira, F., et al.: Biographies, bollywood, boom-boxes and blenders: domain adaptation for sentiment classification. In: ACL, vol. 7, pp. 440–447 (2007)
Chikersal, P., Poria, S., Cambria, E., Gelbukh, A., Siong, C.E.: Modelling public sentiment in twitter: using linguistic patterns to enhance supervised learning. In: Gelbukh, A. (ed.) CICLing 2015. LNCS, vol. 9042, pp. 49–65. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-18117-2_4
Turney, P.D., Littman, M.L.: Measuring praise and criticism: inference of semantic orientation from association. ACM Trans. Inf. Syst. (TOIS) 21, 315–346 (2003)
Bestgen, Y.: Building affective lexicons from specific corpora for automatic sentiment analysis. In: LREC (2008)
Bestgen, Y., Vincze, N.: Checking and bootstrapping lexical norms by means of word similarity indexes. Behav. Res. Methods 44(4), 998–1006 (2012). https://doi.org/10.3758/s13428-012-0195-z
Wiebe, J., Wilson, T., Bell, M.: Identifying collocations for recognizing opinions. In: Proceedings of the ACL-01 Workshop on Collocation: Computational Extraction, Analysis, and Exploitation, pp. 24–31 (2001)
Jaidka, K., Chhaya, N., Wadbude, R., Kedia, S., Nallagatla, M.: BATframe: an unsupervised approach for domain-sensitive affect detection. In: Gelbukh, A. (ed.) CICLing 2017. LNCS, vol. 10762, pp. 20–34. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-77116-8_2
Owoputi, O., O’Connor, B., Dyer, C., Gimpel, K., Schneider, N., Smith, N.A.: Improved part-of-speech tagging for online conversational text with word clusters. Association for Computational Linguistics (2013)
Ramos, J., et al.: Using tf-idf to determine word relevance in document queries. In: Proceedings of the First Instructional Conference on Machine Learning, vol. 242, pp. 133–142 (2003)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 Springer Nature Switzerland AG
About this paper
Cite this paper
Chhaya, N., Jaidka, K., Wadbude, R. (2023). Predicting Email Opens with Domain-Sensitive Affect Detection. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2018. Lecture Notes in Computer Science, vol 13397. Springer, Cham. https://doi.org/10.1007/978-3-031-23804-8_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-23804-8_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23803-1
Online ISBN: 978-3-031-23804-8
eBook Packages: Computer ScienceComputer Science (R0)