Conference Paper

A psychological based analysis of marketing email subject lines

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Emotions and sentiments in the advertisements can contribute a lot to the success or failure of the advertisement. Miller et al. (2017) [3] talks about improving the email marketing strategy by analyzing the psychological effects induced in the email recipient. They identify that the subject line of an email and the email address of the sender are the two major factors which make a receiver to open an email or leave it. ...
... In order to analyze the emotions in the Tweet, we adopted a lexicon based approach which is somewhat similar to the methodology proposed by Miller et al. (2016) [3]. The lexicon-based approach is more accurate and robust than the traditional bag-of-words approach and also we believe it to be a better way to analyze emotions because the emotions cannot be expressed other than using words. ...
... In order to analyze the emotions in the Tweet, we adopted a lexicon based approach which is somewhat similar to the methodology proposed by Miller et al. (2016) [3]. The lexicon-based approach is more accurate and robust than the traditional bag-of-words approach and also we believe it to be a better way to analyze emotions because the emotions cannot be expressed other than using words. ...
Conference Paper
Full-text available
Social media marketing is a form of Internet marketing that utilizes social networking websites as a marketing tool. Marketers post advertisements on social networking websites to promote their products and services. Most often, advertisements on social media are paid advertisements. However, not all advertisements reach the target audience. The gain obtained through advertisements is far less than the expenditure. This study proposes a model to increase the popularity of advertisements posted on social media. The cosmetics industry was taken as the case study and advertisements posted by cosmetics companies on Twitter were studied. This study identifies the most prominent features that impact Twitter advertisements to go viral. In order to reach a larger number of viewers, improvements to these features are suggested.
... Using a Random Forest regressor, the study verified how different keywords on the same subject impacted the open rate, assigning a score to each of them. Miller and Charles (2017) explored the role of the sender's email address and the subject line on the open rate and concluded that they are the primary deciding factors in opening or skipping an email. The authors analyzed email subject lines from a psychological point of view, studying their ''effect in a person when he/she reads it and the decision he/she makes to open that email or neglect it'' (Miller & Charles, 2017). ...
... Miller and Charles (2017) explored the role of the sender's email address and the subject line on the open rate and concluded that they are the primary deciding factors in opening or skipping an email. The authors analyzed email subject lines from a psychological point of view, studying their ''effect in a person when he/she reads it and the decision he/she makes to open that email or neglect it'' (Miller & Charles, 2017). The authors studied the emotional effect of subject lines on the open rate through a lexicon-based approach. ...
Article
Despite being one of the most cost-effective methods, email marketing remains challenging due to the low rate of opened emails and the high percentage of unsubscribed campaigns. Since the sender and the subject line are the only information that the recipient sees at first when receiving an email, the decision to open an email critically depends on these two factors, which should stand out and catch the recipient’s attention. Therefore, the motivation behind this study is to support email campaign editors in choosing a subject line based on its potential quality. We propose and compare several models to measure the quality of a subject line, considering its potential to promote the email opening. The subject lines’ structure and content are explored together with different machine learning techniques (Random Forest, Decision Trees, Neural Networks, Naive Bayes, Support Vector Machines, and Gradient Boosting). To validate the proposed model, a data set of 140,000 emails’ subject lines was used. The results revealed that the models proposed are very promising to support the definition of the email marketing subject lines and show that the combination of data regarding the structure, the content of the subject lines, and senders characteristics leads to more accurate classifications of the potential of the subject line.
... Furthermore, we used fctitious sender names to eliminate familiarity efects on users' reactions to the persuasive tactics. As a result, we could not observe whether users evaluate persuasive tactics diferently when they know or even have engaged with the senders, as the sender's name is indeed an important cue for inbox-level decision-making [69]. Future studies should build on our work to further investigate such contextual factors. ...
... A marketing e-mail becomes a success only if the e-mail receiver opens and reads it (Miller & Charles, 2016). In South Africa, the e-mail average open rate is 25.83%, while the average clickthrough rates is at 3.46%, which indicates that subscribers want to engage (Everlytic, 2017). ...
Article
Full-text available
The paper examines the influence of opt-in e-mail marketing on consumer behaviour. The study attempts to extend the Stimuli–Organism–Response (S–O–R) theory that has been broadly explored in consumer research. Following a critical review of the literature organisation approach, a hypothetical model has been proposed for this study, based on identified factors, such as, informational value, entertainment-based message content, layout, visual appeal, attitude toward e-mail advertising and intention towards the sender in the context of opt-in email marketing. Data were collected in South Africa through an online survey of 436 opt-in e-mail marketing subscribers. Structural equation modelling (SEM) was employed to measure the proposed hypotheses of the study. The research results suggest that even during a pandemic, e-mail marketers could employ certain features in promotional and informational e-mail marketing communication, particularly informational value, entertainment-based message content, layout, visual appeal, as a means to design their e-mail marketing messages and plan e-mail advertising campaigns. The findings of the study are intended to advance the e-mail marketing knowledge base to help marketers during a pandemic, such as COVID-19. The paper provides marketers with relevant insights on how to effectively engage with e-mail subscribers.
... In the following, we hypothesize the effect of some of the important email design elements on consumers' responses and their purchase behavior. Miller and Charles (2016) find that the subject line of any email is one of the major factors that influence consumers' responses to either open or abandon an email. According to a survey by Schultz (2018), consumers want email subject lines to be linguistically correct that convey the gist of the email succinctly. ...
Article
In this research, we empirically explore the effects of various design elements of email newsletters on consumers' email responses and their purchases. We capture the consumers' email responses using three metrics, namely email open, email click, and email reopen. We operationalize consumers' purchases as their spending on product items that are featured in email newsletters. Using a novel email marketing database, first, we model the influence of design elements of email newsletter on consumers' email responses at the individual consumer level. The email design elements constitute several email attributes, situational factors, and integrated marketing communication. Second, we quantify the effects of these three email responses, open, click, and reopen, on consumers' purchases. Our empirical results suggest a significant influence of email attributes, situational factors, and marketing communications on consumers' email responses. Furthermore, among open, click, and reopen, we find clicks tend to have the highest impact on consumers’ purchase, followed by email reopening and opening. However, email newsletters with higher opening probability are more effective in influencing purchases than those email newsletters with higher reopening probability. Furthermore, consumers who indulge in all three email responses, namely opening, clicking, and reopening, tend to purchase the most. Results from our study offer several critical insights for email marketing strategy helping managers improving the effectiveness of email campaigns by careful consideration for the design elements of email newsletters.
... In this work, we use a subset of this publicly available dataset. Enron has been a very popular dataset for social network analysis (Chapanond et al., 2005;Diesner et al., 2005;Shetty and Adibi, 2005;Oselio et al., 2014;Ahmed and Rossi, 2015) and sentiment and authority analysis (Diesner and Evans, 2015;Liu and Lee, 2015;Miller and Charles, 2016;Mohammad and Yang, 2011). Peterson et al. (2011) present an approach to model formality on the ENRON corpus and Kaur et al. (2014) compare emotions across formal and informal emails. ...
... The literature exploring the relationship between the language of emails and recipient behavior has drawn on mixed methods to offer linguistic and predictive insights into the best strategies for garnering email responses. The paper by Miller and Charles [21] provides a qualitative analysis of 150 personal emails from the Enron email dataset 3 and 150 spam emails from the Spamdex dataset 4 , to propose 40 rules for improving the impact of marketing emails. However, these qualitative analyses are necessarily small in scope, and do not compare between the best strategies for different types of businesses. ...
Conference Paper
Marketing practices have adopted the use of computational approaches in order to optimize the performance of their promotional emails and site advertisements. In the case of promotional emails, subject lines have been found to offer a reliable signal of whether the recipient will open an email or not. Clickbait headlines are also known to drive reader engagement. In this study, we explore the differences in recipients' preferences for subject lines of marketing emails from different industries, in terms of their clickthrough rates on marketing emails sent by different businesses in Finance, Cosmetics and Television industries. Different stylistic strategies of subject lines characterize high clickthroughs in different commercial verticals. For instance, words providing insight and signaling cognitive processing lead to more clickthroughs for the Finance industry; on the other hand, social words yield more clickthroughs for the Movies and Television industry. Domain adaptation can further improve predictive performance for unseen businesses by an average of 16.52% over generic industry-specific predictive models. We conclude with a discussion on the implications of our findings and suggestions for future work.
... 1) Emotions Analysis : : We analyze emotions that the writer of a post tries to express [6]. In the field of Natural Language Processing, the basic emotions are categorized into six groups -"anger", "fear", "sadness", "enjoyment", "disgust" and "surprise" [7]. ...
Chapter
Email marketing works as a top channel to generate leads for many businesses. The marketing automation platforms are part of this strategy and can improve the success of email campaigns. Many of these platforms use subject line tools to predict if an email will be opened or not, as a success metric. However, the text content is unused. Thus, this work proposes to predict the likelihood of a user clicking the Call to Action button of an email based on the content. We implement our proposal in a real-case scenario of corporate communication emails from a private university in Mexico. After building a machine learning model, the results were promising and validated our proof-of-concept. We consider the results relevant for further investigation around other ways to improve the success of an email using the text content, and this model could be reliable in most campaigns and could be used to determine which words influence the click rate metric the most.
Chapter
Natural language resources are essential for integrating linguistic engineering components into information processing suites. However, the resources available in French are scarce and do not cover all possible tasks, especially for specific business applications. In this context, we present a dataset of French newsletters and their use to predict their impact, good or bad, on readers. We propose an original representation of newsletters in the form of graphs that take into account the layout of the newsletters. We then evaluate the interest of such a representation in predicting a newsletter’s performance in terms of open and click rates using graph convolution network models.
Article
Full-text available
Email is one of the most popular modes of communication we have today. Billions of emails are sent every day in our world but not every one of them is relevant or of importance. The irrelevant and unwanted emails are termed email spam. These spam emails are sent with many different targets that range from advertisement to data theft. Filtering these spam emails is very essential in order to keep the email space fluent in its functioning. Machine Learning algorithms are being extensively used in the classification of spam emails. This paper showcases the performance evaluation of some selected supervised Machine Learning algorithms namely Naive Bayes Classifier, Support Vector Machine, Random Forest, & XG-Boost for spam email classification on a combination of three different datasets. For feature extraction, both Bag of Words & TF-IDF models were used separately and performance with both of these approaches was also compared. The results showed that SVM performed better than all the other algorithms when trained with TF-IDF feature vectors. The performance metrics used were accuracy, precision, recall, and f1-score, along with the ROC curve.
Article
Objective: To examine whether manipulating the frame used in email subject lines affects open or click-through rate. Participants: Students (N = 38,538) at a Midwestern university received emails from their health clinic about a stress management program (September - December 2017). Method: Three subject lines (Action Instruction only, Gain Frame plus Action Instruction, Non-loss Frame plus Action Instruction) were used. Each student randomly received one subject line in the first two months and one in the next two months. Email open and click-through rates were measured. Results: Emails with the Action Instruction only subject line were more likely to be opened; there was no difference in open rate between the two framed subject lines, and no effect on click-through rates. Conclusion: This study supports the benefits of action instructions to encourage behavior change but calls for further research on the effects of frames and action instructions in email subject lines.
Conference Paper
Full-text available
Email is a ubiquitous communication tool and constitutes a significant portion of social interactions. In this paper, we attempt to infer the personality of users based on the content of their emails. Such inference can enable valuable applications such as better personalization, recommendation, and targeted advertising. Considering the private and sensitive nature of email content, we propose a privacy-preserving approach for collecting email and personality data. We then frame personality prediction based on the well-known Big Five personality model and train predictors based on extracted email features. We report prediction performance of 3 generative models with different assumptions. Our results show that personality prediction is feasible, and our email feature set can predict personality with reasonable accuracies.
Article
Full-text available
We present a lexicon-based approach to extracting sentiment from text. The Semantic Orientation CALculator (SO-CAL) uses dictionaries of words annotated with their semantic orientation (polarity and strength), and incorporates intensification and negation. SO-CAL is applied to the polarity classification task, the process of assigning a positive or negative label to a text that captures the text's opinion towards its main subject matter. We show that SO-CAL's performance is consistent across domains and in completely unseen data. Additionally, we describe the process of dictionary creation, and our use of Mechanical Turk to check dictionaries for consistency and reliability.
Article
Full-text available
Sentiment analysis of microblogs such as Twitter has recently gained a fair amount of attention. One of the simplest sentiment analysis approaches compares the words of a posting against a labeled word list, where each word has been scored for valence, -- a 'sentiment lexicon' or 'affective word lists'. There exist several affective word lists, e.g., ANEW (Affective Norms for English Words) developed before the advent of microblogging and sentiment analysis. I wanted to examine how well ANEW and other word lists performs for the detection of sentiment strength in microblog posts in comparison with a new word list specifically constructed for microblogs. I used manually labeled postings from Twitter scored for sentiment. Using a simple word matching I show that the new word list may perform better than ANEW, though not as good as the more elaborate approach found in SentiStrength.
Book
The Handbook of Natural Language Processing, Second Edition presents practical tools and techniques for implementing natural language processing in computer systems. Along with removing outdated material, this edition updates every chapter and expands the content to include emerging areas, such as sentiment analysis. New to the Second Edition • Greater prominence of statistical approaches • New applications section • Broader multilingual scope to include Asian and European languages, along with English • An actively maintained wiki (http://handbookofnlp.cse.unsw.edu.au) that provides online resources, supplementary information, and up-to-date developments Divided into three sections, the book first surveys classical techniques, including both symbolic and empirical approaches. The second section focuses on statistical approaches in natural language processing. In the final section of the book, each chapter describes a particular class of application, from Chinese machine translation to information visualization to ontology construction to biomedical text mining. Fully updated with the latest developments in the field, this comprehensive, modern handbook emphasizes how to implement practical language processing tools in computational systems.
Article
Computational advertising uses information on web-browsing activity and additional covariates to select advertisements for display to the user. The statistical challenge is to develop methodology that matches ads to users who are likely to purchase the advertised product. These methods not only involve text mining, but also may draw upon additional modeling related to both the user and the advertisement. This paper reviews various aspects of text mining, including n-grams, topic modeling, and text networks, and discusses different strategies in the context of specific business models. © 2013 Wiley Periodicals, Inc. Statistical Analysis and Data Mining, 2013
Conference Paper
Automated classication of email messages into user-specic folders and information extraction from chronologically ordered email streams have become interesting areas in text learning research. However, the lack of large benchmark collections has been an obstacle for studying the problems and evaluating the solutions. In this paper, we introduce the Enron corpus as a new test bed. We analyze its suitability with respect to email folder prediction, and provide the baseline results of a state- of-the-art classier (Support Vector Machines) under various conditions, including the cases of using individual sections (From, To, Subject and body) alone as the input to the classier, and using all the sections in combination with regression weights.
Article
An important part of our information-gathering behavior has always been to find out what other people think. With the growing availability and popularity of opinion-rich resources such as online review sites and personal blogs, new opportunities and challenges arise as people now can, and do, actively use information technologies to seek out and understand the opinions of others. The sudden eruption of activity in the area, of opinion mining and sentiment analysis, which deals with the computational treatment of opinion, sentiment, and subjectivity in text, has thus occurred at least in part as a direct response to the surge of interest in new systems that deal directly with opinions as a first-class object. This survey covers techniques and approaches that promise to directly enable opinion-oriented information-seeking systems. Our focus is on methods that seek to address the new challenges raised by sentiment-aware applications, as compared to those that are already present in more traditional fact-based analysis. We include material on summarization of evaluative text and on broader issues regarding privacy, manipulation, and economic impact that the development of opinion-oriented information-access services gives rise to. To facilitate future work, a discussion of available resources, benchmark datasets, and evaluation campaigns is also provided.
Email and Facebook Consumer Pulse Report
  • Facebook Email
  • Consumer
Email and Facebook Consumer Pulse Report
  • Chadwick Martin Bailey
Chadwick Martin Bailey, Email and Facebook Consumer Pulse Report 2012 [Online], Available: http://www.cmbinfo.com/assets/Email-and-Facebook-Consumer-Pulse-Report2012.pdf