=Paper=
{{Paper
|id=Vol-1618/DC_1
|storemode=property
|title= Improving E-Commerce User Experience with Data-Driven Personalized Persuasion & Social Network Analysis
|pdfUrl=https://ceur-ws.org/Vol-1618/DC_1.pdf
|volume=Vol-1618
|authors=Ifeoma Adaji
|dblpUrl=https://dblp.org/rec/conf/um/Adaji16
}}
== Improving E-Commerce User Experience with Data-Driven Personalized Persuasion & Social Network Analysis ==
https://ceur-ws.org/Vol-1618/DC_1.pdf
Improving E-Commerce User Experience with Data-Driven
Personalized Persuasion & Social Network Analysis
Ifeoma Adaji
University of Saskatchewan
Saskatchewan, Canada
ita811@mail.usask.ca
ABSTRACT persuasive to customers with the aim of increasing the success of e-
Simply selling products online can no longer guarantee profits for businesses.
e-businesses especially for new comers to the e-commerce industry,
as the competition among companies is more intense. In order to
2. RESEARCH OBJECTIVES
keep existing customers and make new ones, e-businesses have to Companies collect data of their clients including demographics data,
provide products and services that feel personal to their clients. This browsing patterns, product reviews and ratings, and purchase
research proposes a framework for improving a user’s e-commerce history. This data is a huge repository of information and can tell a
experience by using personalized persuasion techniques and social company a lot about their clients. In addition, a large proportion of
network analysis. The proposed framework proposes the use of online shoppers are active social media users. These users also
persuasion profiles in implementing a customer segmentation generate a lot of online data that companies can take advantage of
strategy. The framework also proposes the analysis of social in designing products and services to meet their customers’ needs. I
networks to improve customers’ shopping experience. propose to develop a data driven framework to support a dynamic
personalized persuasion approach. Using user generated data, this
Keywords research will answer questions such as:
User modelling, personalization, persuasive technology, social 1. How likely is a customer to complete a purchase in a session?
network analysis 2. How focused or distracted does the customer appear to be?
3. How likely is it that the customer leaves the site?
1. INTRODUCTION To investigate how to deliver a persuasive message in e-commerce
E-businesses can stay ahead of their competitors by offering in the right way, my research will focus on human behavior through
personalized products and services tailored to individual users using design and user studies addressing these questions:
existing data about their clients, recommender systems and 1. What influence strategies can be adopted in displaying a
persuasive technology [1]. Recommender systems suggest products product in e-commerce?
to users according to their interests. However, research shows that 2. How do people respond to these strategies?
the most accurate recommender algorithms do not always generate 3. How can we measure people’s response to the various ways in
choices that the users are satisfied with [2]. Many factors, including which product information is presented?
the way recommended products are presented to a client play a role
in whether a customer will eventually buy the product [3], [4]. In The potential contributions of this proposed research will be
essence, the presentation of an online product to a customer is key important and novel for several reasons:
in the final purchase decision of the client. As the client is not able 1. Personalized Persuasion in the context of e-commerce has not
to touch the product as he/she would do in a brick and mortar store, been researched sufficiently so far.
it is essential that items are presented to online clients in a way that 2. A novel method for data-driven user behavior modeling in the
they are encouraged to buy it. Persuasive technology attempts to area of e-commerce will be developed that will be able to
favorably change the clients’ perception of products or services to achieve e-commerce success in terms of the four core success
convince them to buy the items or use the services. Since the target metrics of e-businesses; customer loyalty, conversion,
audience for persuasive systems are usually heterogeneous, a one- retention and average order size [7].
size-fits-all approach is usually ineffective [5]. As people differ in 3. A novel method for building user persuasive profiles based on
their motivations and perceptions; in order to be successful, their susceptibility to visual and strategic persuasion will be
persuasive technologies need to be tailored to the individual user [4]. developed, that will be used for tailoring the display and
persuasive interventions to optimize the user experience in the
Fogg and Eckles [6] suggest that for a persuasion technique to be
e-commerce system.
effective, it has to deliver 1) the right message 2) at the right time
and 3) in the right way. Online recommendation systems focus on This research will lead to results that will be beneficial to new and
1) delivering the right message; generating suggestions about existing e-commerce businesses.
products that are tailored to a user’s interests, based on their history
of interactions. My proposed research studies parts 2) and 3) of Fogg 3. PROPOSED SOLUTION
and Eckles’ definition of an effective persuasive system; delivering The aim of this research is to improve the success of e-businesses.
a message at the right time and in the right way, bearing in mind that In order to achieve this, I propose a framework which implements
both the right time and the right way differ from one individual to persuasive interventions and mines social media data as shown in
another. figure 1.
This research aims at developing a framework that will make To implement the persuasive technology module of the proposed
product selection and presentation more personalized and framework, I intend to use the Persuasive Systems Design model
[8]. Although there are currently several frameworks and strategies
for designing persuasive systems in different domains, I choose to the customers. This will be done using data mining techniques with
use this model for two reasons. First, the framework this model was data from the popular social networks.
derived from, Fogg’s functional triad [9], has been studied
extensively over the years, but there is little or no research on newer This proposed system, including the effectiveness of the persuasive
models derived from it. Second, as noted by Oinas-Kukkonen and techniques, will be evaluated using the four core success metrics of
Harjumaa [8], Fogg’s framework and principles are too general to e-businesses; customer loyalty, conversion, retention and average
be useful in designing and evaluating persuasive systems. order size [7].
4. RELATED WORK
My research aims at improving the persuasiveness of an e-business
by adopting several principles of the Persuasive Systems Design
(PSD) framework for designing and evaluating persuasive systems.
The PSD framework categorizes and maps the elements of
persuasion in a system and also describes the software functionality
expected in the end product [8]. The framework consists of 28
persuasive principles categorized according to the task they are to
accomplish. The PSD framework, though partly derived from B.J.
Fogg’s functional triad [9], is different from it. The PSD framework,
Figure 1: Proposed framework unlike B.J. Fogg’s functional triad, suggests how the principles of
persuasion can and should be translated to software requirements
Table 1. Persuasive principles1 of the PSD framework which are thereafter implemented as features of the system [8]. To
Primary Task Dialogue Social System the best of my knowledge, there is currently no e-commerce
Support Support Support Credibility platform developed based on this model. On the other hand,
Support Cialdini’s six principles of persuasion [10] have been used
extensively in various domains. I however did not adopt this model
Reduction Praise Social Trustworthiness because the principles are not extensive and do not suggest possible
learning
implementation as systems features, while the PSD framework does.
Tunneling Rewards Social Expertise In order to give customers relevant shopping experiences that feels
comparison personal to them, I propose to use personalization. There have been
Tailoring Reminders Normative Surface several attempts at personalization in the past. Kaptein and Parvinen
influence credibility [11] developed a process framework for personalization in e-
commerce. Their implementation of personalization is similar to
Personalization Suggestion Social Real-world feel that of the PSD framework, hence I adopted it in my research. They
facilitation suggest that for personalization in e-commerce to be successful, it
Self-monitoring Similarity Cooperation Authority should have a positive effect on the outcome of the business, this
effect should be different between customers and the effect on
Simulation Liking Competition Third-party clients should be stable.
endorsement
To ensure that the effect of personalization is different among users,
Rehearsal Social role Recognition Verifiability several researchers have adopted the use of persuasion profiles, also
referred to as personas [7], [4], [1], [12], [13], [14]. Persuasion
The PSD framework consists of 28 persuasive principles grouped profiles use persuasive strategies and data such as demographic
into four categories based on the task the principle aims to information, purchase patterns, buying history, click behavior and
accomplish. Table 1 lists the principles and their categories. Though shopping cart items of clients to personalize their shopping
this model comprises of several persuasive techniques, I propose to experience [7]. Kaptein et al [4] implemented persuasion profiles by
include (or exclude) other principles, like visual contrast, that might evaluating the effect of several persuasive principles on a user. They
enhance the persuasiveness of the proposed system. implemented both explicit and implicit profiling. In explicit
profiling, the user has to fill out a questionnaire stating their
To implement the social media module of the framework, I propose preferences before using the system. With implicit profiling, the
to use two methods. First is to implement an internal social network system infers the user’s preferences based on actions and responses
in the proposed e-commerce platform as is evident in successful e- of the user. My proposed implementation of persuasion profiles is
commerce companies like Amazon and E-bay. The internal social implicit using data such as demographic information, purchase
network will provide a medium for customers to interact with each patterns, buying history, click behavior and shopping cart items of
other, ask questions about products, read and write reviews and earn clients when they launch the e-commerce platform. It however
virtual rewards. This is to enhance user participation which could differs from Kaptein et al’s implementation because while they used
lead to more sales for the e-business. The second implementation only six influence principles to build the user’s profile, I propose to
method I propose is to take advantage of existing social networks in use a combination of the 28 influence principles of the PSD model
order to understand current business trends from the view point of as described in figure 1. While the customer browses products on
the e-commerce platform, products will be displayed with a
combination of several of these principles until a profile is generated
1 The authors defined these as principles. For a detailed explanation
of these principles, please see [8]
successfully for the user. The selection will be based on the user’s product recommendations to clients, one can opt for products with
response to the principles at runtime. mixed reviews as these reviews are perceived to be more trustworthy
and hence could be more persuasive to the customer.
5. PROGRESS AND FUTURE RESEARCH In evaluating the success of the personalized persuasive
This research aims at improving the success of e-business
interventions generated by my proposed framework, I propose to
companies by enhancing users’ experience with data-driven
adopt the core metrics for e-commerce success of [7]: loyalty,
personalized persuasion and social network analysis. I propose to
conversion, retention and average order size. In order to ensure
achieve this using the framework described in Figure 1 and the
customer retention, it is imperative to predict customer churn; when
success metrics; customer loyalty, conversion, retention and average
a client is no longer satisfied with doing business with a company
order size.
and decides to stop using their service. Being able to predict
5.1 Progress Made So Far customer churn is important as it will enable the e-businesses put
To gain insight into designing the persuasive module, I evaluated strategies in place to prevent the loss of customers. In a study I
carried out on e-commerce data, I was able to identify what data
two well-known systems using the PSD framework. Using Stack
mining algorithm to use for churn prediction in e-commerce. The
Overflow as a case study, I identified how the persuasive principles
result of the study is under review for publication in an e-commerce
of the PSD framework were implemented in a question and answer
journal.
social network [15]. All but four of the 21 principles I investigated
were identified in Stack Overflow2. This study is important because Since high quality answers keep a question and answer forum active,
the proposed solution will incorporate a social network module it is also important to identify and predict the churn of expert
where users can ask and answer questions in addition to review respondents; the users who give the best answers to most of the
products and earn points. Knowing how a successful question and questions. In view of this, I conducted a study on a successful
answer social network implements persuasion will be beneficial in question and answer social network, Stack overflow. This study [19]
the design of the internal social network module of my proposed identifies expert respondents and successfully predicts their churn
solution. I am currently extending this work by carrying out a user using data mining techniques. This study is essential to my research
study where the implementations of the identified persuasive because the social network module is an integral part of the proposed
principles will be validated by Stack Overflow users. This user study solution and research has shown that overall success of a business is
will determine the persuasiveness or otherwise of these persuasive partly owed to a successful social media strategy [20].
principles.
5.2 Future Research
In order to discern the implementation of persuasion in a typical e-
Over the next several months, my focus will be on identifying the
commerce platform, I evaluated Amazon’s persuasion strategies
personalization and persuasive strategies that work best together in
using the PSD framework [16]. In this study, I was able to identify
both e-commerce and social networks. I will do this by conducting
all 21 principles of persuasion that were investigated. Furthermore,
several user-studies where users will be asked to answer questions
I was also able to identify the personalization strategies
based on their experience of using different e-commerce and social
implemented by Amazon in tailoring content and recommendations
network platforms. In one of the studies, users will be presented with
to users’ preferences. This study is very important to my research as
image and text product descriptions and will be asked to identify
it sheds light on what strategies I can adopt in my proposed solution
which ones they find more persuasive and why.
to enhance personalization and successfully implement the
persuasive principles of the PSD framework. The study on Amazon Since persuasion profiles are an integral part of providing
is still in progress; I am working on a user-study that will enable personalized content to customers, I will work on designing and
users describe the effect of the identified personalization strategies implementing dynamically generated persuasion profiles for users
on them and identify the persuasive principles that work best. This with the aim of answering the following research questions.
is important in creating a personalized user experience. 1. How can one apply the data-driven user model and the
persuasion profile to generate a personalized persuasive
The System Credibility Support persuasive principles of the PSD
product display? In other words, can a system dynamically
framework deserve special attention in the context of e-commerce.
apply a user’s persuasion profile when presenting information
My PhD research will incorporate visual complexity contrast as one
about a selected product?
of the persuasive strategies to be implemented in the proposed
2. How can one evaluate the effectiveness of the user’s
model. Visual complexity contrast refers to how complex an image
personalization experience?
is compared to surrounding images [17]. A study I conducted with
colleagues in our group [3] reveals that visual persuasion can be Answering these questions will involve reading vast literature on the
achieved through visual complexity contrast. This conclusion is subject of persuasion profiles. In addition, it will involve carrying
important in designing the proposed system to ensure that products out user-studies to validate the effectiveness of existing
are presented to users in a way that will positively influence them to implementations of persuasion profiles.
buy the products.
In another study carried out in our group, I investigated customer
6. CONCLUSION
trust in reviewers’ credibility [18]. This study revealed, among other Simply selling products online can no longer guarantee profits for
conclusions, that reviewers with mixed positive and negative e-businesses especially for new comers to the e-commerce industry.
reviews tends to be perceived as being more trustworthy. The result Since e-commerce is now a mainstream activity, the competition
of this study is important as it can be used to implement persuasion among companies is more intense. Consequently, e-businesses have
profiles that are tailored to the users’ preferences. Persuasion to adopt strategies that can enhance the shopping experience of their
profiles will also ensure that the right content is presented to the user customers that will subsequently translate to profits for the e-
at the right time and in the right way. For example, when displaying business. My research aims at improving e-commerce users’
2 For this study, I only investigated 21 of the 28 principles
experience using data-driven personalized persuasion and social [9] B. Fogg, Persuasive Technology: Using Computers To
network analysis. Change What We Think and Do, Morgan Kaufmann
I propose to use a framework that combines persuasive technology Publishers, 2003.
and social network analysis to provide an e-commerce platform that 10] R. B. Cialdini, Influence: Science and Practice., Boston:
will deliver the right content to a user at the right time and in the Pearson Education, 2009.
right way. The persuasive technology module will implement
personalization and persuasive strategies based on the PSD [11] M. Kaptein and P. Parvinen, "Advancing E-commerce
framework. The social media module will incorporate a social Personalization: Process Framework and Case Study,"
network on the proposed e-business platform that will allow for International Journal of Electronic Commerce, vol. 19, no. 3,
communication between customers. pp. 7-33, 2015.
The contributions of this research are novel and relevant because [12] M. Kaptein, "Adaptive persuasive messages in an e-
they will introduce an innovative approach for generating content commerce setting: the use of persuasion profiles,"
for users in e-commerce that is data-driven and personalized. When Proceedings of the 19th International Conference on
implemented, my proposed solution will lead to an improved user Information Systems, 2011.
experience in an e-commerce platform.
[13] M. Kaptein, D. Eckles and J. Davis, "Envisioning persuasion
7. REFERENCES profiles: challenges for public policy and ethical practice,"
[1] M. Kaptein and P. Petri, "Dynamically Adapting Sales ACM Interactions, vol. 18, no. 5, pp. 66-69, 2011.
Influence tactics in E-Commerce," Marketing Dynamism &
Sustainability: Things Change, Things Stay the Same, pp. [14] M. Kaptein, P. Markopoulos, B. d. Ruyter and E. Aarts, "Can
445-454, 2015. you be persuaded? Individual differences in susceptibility to
persuasion," Human-computer interaction–INTERACT, pp.
[2] A. Gunawardana and G. Shani, "A Survey of Accuracy 115-118, 2009.
Evaluation Metrics of Recommendation Tasks," Journal of
Machine Learning Research, vol. 10, pp. 2935-2962, 2009. [15] I. Adaji and J. Vassileva, "Persuasive Patterns in Q&A Social
Networks," in Proceedings of the 11th international
[3] K. Wu, J. Vassileva, Y. Zhao, Z. Noorian, W. Waldner and I. conference on Persuasive Technology, Salzsburg, Austria,
Adaji, "Complexity or simplicity? Designing product pictures 2016.
for advertising in online marketplaces," Journal of Retailing
and Consumer Services, vol. 28, pp. 17-27, 2016. [16] I. Adaji and J. Vassileva, "Evaluating personalization and
Persuasion in E-Commerce," in Extended proceedings of the
[4] M. Kaptein, P. Markopoulos and B. d. R. Emile Aarts, 11th international conference on persuasive technology.,
"Personalizing persuasive technologies: Explicit and implicit Salzsburg, Austria, 2016.
personalization using persuasion profiles," International
Journal of Human-Computer Studies, vol. 77, pp. 38-51, [17] C.-T. Kao and M.-Y. Wang, "The right level of complexity in
2015. a banner ad: Roles of construal level and fluency," Human
Interface and the Management of Information. Information
[5] S. Berkovsky, J. Freyne and H. Oinas-Kukkonen, and Interaction Design, pp. 604-613, 2013.
"Influencing Individually:Fusing Personalization and
Persuasion," in Proceedings of 24th Int'l Joint Conference on [18] K. Wu, Z. Noorian, J. Vassileva and I. Adaji, "How buyers
Artificial Intelligence, 2015. perceive the credibility of advisors in online marketplace:
review balance, review count and misattribution," Journal of
[6] B. Fogg and D. Eckles, "Mobile Persuasion: 20 Perspectives Trust Management, vol. 2, no. 1, pp. 1-18, 2015.
on the Future of behavior Change," Stanford Captology
Media, 2007. [19] I. Adaji and J. Vassileva, "Predicting Churn of Expert
Respondents in Social Networks: A Case Study of Stack
[7] "How to Win Online: Advanced Personalization in E- overflow," in IEEE 14th International Conference on
commerce," ATG Web Commerce, An Oracle White Paper, Machine Learning and Applications (ICMLA), Miami,
2011. Florida, 2015.
[8] H. Oinas-Kukkonen and H. Marja, "A systematic framework [20] E. Qualman, Socialnomics: How social media transforms the
for designing and evaluat-ing persuasive systems," in way we live and do business, John Wiley & Sons, 2010.
Proceedings of the 3rd Int'l Conference on Persuasive
Technology, Oulu, Finland, 2008.