Construal Level Theory and Maslow's Hierarchy with Machine
Learning for Enhanced Consumer Demand Analysis
Xin Chen
a
School of Business, University of Sydney, 361 Sussex Street, Sydney, Australia
Keywords: Construal Level Theory (CLT), Maslow's Hierarchy of Needs, Brand Differentiation, Supervised
Classification Learning, Psychological Labeling.
Abstract: This study delves into the intersection of Construal Level Theory (CLT) and Maslow's Hierarchy of Needs
through the lens of advanced machine learning. By adopting psychological labeling and supervised
classification learning, it engages with Maslow's model to scrutinize the market's terrain—differentiating
emergent brands from established counterparts and examining the fulfillment of consumer needs. This inquiry
provides a granular view of how brands cater to the various psychological and spatial dimensions outlined by
Maslow and CLT. The fusion of these psychological frameworks with computational analytics serves to shed
light on the subtleties of brand performance and consumer preferences. The methodology bridges the gap
between abstract psychological theories and their tangible implications in machine learning. The resultant
insights afford a richer comprehension of consumer behavior, equipping businesses with the means to fine-
tune their marketing endeavors. The enhanced understanding gained through this interdisciplinary approach
paves the way for more targeted marketing interventions, thereby improving business decision-making
processes and fostering more effective consumer engagement.
1 INTRODUCTION
As psychological research has deepened our
understanding of how psychological processes affect
behaviors in various fields such as communication,
memory, decision-making, and emotion (British
Psychological Society, 2021), people are increasingly
interested in applying these insights to consumer
research. This method helps to better understand the
intricacies of consumers' personal thoughts, desires,
and experiences (Malter et al., 2020).
In addition, psychology has recognized the great
potential of machine learning to explain theoretical
constructs and build more dynamic and predictive
models (Yarkoni & Westfall, 2017). This paper
proposes to combine CLT and Maslow demand
hierarchy theory with machine learning technology.
These methods can handle complex nonlinear
relationships and huge data sets to better understand
consumer needs.
Our goal is to explore how to apply these
advanced technologies to enhance the brand's product
a
https://orcid.org/0009-0007-0483-4239
strategy, improving efficiency as well as addressing
the psychological and emotional contours of
consumer decisions. As a result of such integration,
the interaction between the brand and the consumer
should be closer to their psychology, as well as
increase artificial intelligence's ability to understand
and respond to the subtle needs of digital users.
2 BACKGROUND AND RELATED
WORK
This chapter explains three theories, starting with
objects as part of the extension of the self, as a means
of rationalizing the movement toward ownership,
control, and proximity in the theory of mental
framing, and proposing Maslow's needs as a model
for a staged interpretation of consumer needs. This is
used as a theoretical basis for the following chapter
on mental labeling.
188
Chen, X.
Construal Level Theory and Maslow’s Hierarchy with Machine Learning for Enhanced Consumer Demand Analysis.
DOI: 10.5220/0012922800004508
Paper published under CC license (CC BY-NC-ND 4.0)
In Proceedings of the 1st International Conference on Engineering Management, Information Technology and Intelligence (EMITI 2024), pages 188-193
ISBN: 978-989-758-713-9
Proceedings Copyright © 2024 by SCITEPRESS Science and Technology Publications, Lda.
2.1 Theories
2.1.1 Sartre and Belk
In his 1988 study, Property and the Extended Self,
Belk explores how objects play an integral role in
who we are and introduces the concept of the
extended self as an extension of us. In addition to
examining individual ownership of objects, the study
examines the way we relate to them from a broader
perspective. Objects define our sense of self, as the
writer Yi-Fu Tuan (1980) points out, because we are,
in a large part, what we own and possess. He states,
"Our fragile sense of self needs support, and we get
that support by owning and possessing objects."
It is advisable to keep all the given values. Belk's
view further clarifies how objects are seen as an
extension of our self-concept, from a part of our body
to the physical environment around us. According to
Jean-Paul Sartre's (1943) theory, the ways in which
objects become "extensions of the self" primarily
involve controlling, creating, and making sense of
them. These processes extend beyond the individual
to include collective identities such as families,
groups, subcultures and nations. David (1951)
suggests that by creating or deeply understanding an
object, an individual can internalize it as part of their
own identity. This involves both the creation of
material objects and abstract concepts and the process
of becoming intimate with the object and seeing it as
part of the self.
Belk's (1988) research suggests that by owning
and controlling objects, consumers effectively reduce
the psychological distance between themselves and
those objects. For example, by knowing and
customizing a smartphone to reflect personal tastes
and preferences, an individual may feel that the phone
is an integral part of him or her, thereby significantly
reducing the psychological distance from the object.
2.1.2 Construal Level Theory
The core motivation for viewing objects as extensions
of the self is partly motivated by the quest for
completeness, which evolves into control and
possession of objects. This dovetails with Construal
Level Theory (CLT), which focuses on narrowing
psychological distances and emphasizes four types of
distances - temporal, social, spatial, and hypothetical
- that converge psychologically to form psychological
distances that influence decision-making in different
contexts.
Jean-Paul Sartre (1943) theorized that controlling
and owning objects effectively reduces the
psychological distance between us and those objects.
Ownership extends beyond the physical to include the
perception of consumer goods, their personalization,
and their reflection of one's identity and social status.
For example, personalizing smartphone settings to
reflect personal preferences makes the phone an
integral part of the individual, thus significantly
reducing psychological distance. Psychological
distance is positively related to the level of mental
representation an individual establishes of an object,
event, or person (Sordi et al., 2022).
Influenced by emotional or cognitive processes,
consumer decision-making varies depending on the
level of abstraction of their thinking, with higher
levels of abstraction preferring modern products that
are feature-rich (Ding et al., 2017). Direct experience
with a product shortens the psychological distance
and makes the consumer's interaction with the
product more concrete (Trope & Liberman, 2010).
Combined with the insights of Sam Maglio
(2019), psychological distance also influences how
consumers envision and act on possibilities. Even at
the initial decision-making stage, this distance can
cause systemic shifts, as what is psychologically
distant must be mentally visualized, while what is
close can be directly observed. For organizations,
managing social distance is critical to managing
relationships with customers, and it influences how
consumers perceive brands that are psychologically
close or distant. Therefore, understanding and
applying cultural communication techniques can
have a significant impact on marketing strategy and
consumer engagement by addressing the
psychological distance that affects consumer
perception and behavior.
2.1.3 Maslow Demand
When discussing consumer goods as extensions of the
self, it is clear that the symbolism of consumer goods
varies over time, cultures, and individual and
collective contexts. Such variations reflect the
diversity exhibited by the different characteristics and
attributes of consumer goods. Maslow's (1943)
Hierarchy of Needs describes human needs as ranging
from basic physiological needs like food and air to
higher level needs like self-esteem and self-
actualization.
Jordan (1999) extended this framework to the
hierarchy of needs of product users, defining levels of
functionality, usability, and pleasure, highlighting
how products evolve to satisfy these multiple levels
of human needs. Oghenemaro (2023) updated
Maslow's hierarchy of needs by emphasizing that
Construal Level Theory and Maslow’s Hierarchy with Machine Learning for Enhanced Consumer Demand Analysis
189
once the individual has met the basic needs, he
progressively seeks to satisfy more complex needs
that motivate behavior until self-actualization. This
refined understanding allows us to better recognize
and satisfy the different needs of consumers and to
understand the tendency of products to migrate to
higher Maslowian needs during their gradual
formation and maturation.
By further exploring Maslow's Hierarchy Theory,
we can categorize needs into multiple dimensions,
such as product value, social value and personal
value, thus laying a solid foundation for
understanding consumer behavior and designing
products and services that satisfy these needs.
2.2 Gaps
2.2.1 Theoretical Gaps
The theoretical gaps identified through the review and
analysis of the existing literature suggest that while
Construal Level Theory (CLT) has been widely used
in various fields, especially in marketing and online
retailing through high-frequency word analysis, there
is a relative paucity of research on the intersection of
CLT and consumer behavior. Furthermore, an
important theoretical gap in the consumer decision-
making process relates to the mental representation of
unchosen alternatives. Existing literature emphasizes
how mental representations of situations influence
product choice, but there is still little discussion on
how non-selective decisions are constructed. For
example, Sordi et al. (2022) argue that consumers
may also employ rejection strategies that
systematically eliminate options until a final choice is
made. As noted by Mourali & Nagpal (2013), such
strategies can produce different outcomes even when
the same set of options is considered.
Cultural linguistics has been used in many
different domains, but few studies combine its
analysis with other theories or models (such as
Maslow's Hierarchy of Needs) or with artificial
intelligence to model and annotation consumer
demand. There is an urgent need for research that
explores the intricate relationship between culture
and consumer behavior, with a particular focus on
how to incorporate machine learning to analyze
consumer demand and the corresponding product
offering strategies of brands.
2.2.2 Methodology Gaps
In relation to Maslow's classification of needs,
Jastrzebska and Homenda (2012) provide a detailed
categorization of needs, including applying Maslow's
Hierarchy Theory to their model to quantify the
impact of needs on an individual's behavior on a scale
of zero to one. They categorized needs into
physiological, safety, love and belonging, esteem and
self-actualization needs and defined these needs
throughout the needs space. This helps to differentiate
consumer need vectors based on their similarities and
dissimilarities and provides a methodological basis
for further exploration of consumer similarity
measurement.
However, there are obvious limitations to these
models, as well as the fact that the research relies
primarily on qualitative rather than quantitative
analysis, which results in a lack of relevant word
frequencies to label needs and limits the effective
integration of consumer cues into the algorithm. In
addition, while cluster analysis has been used to
identify CLT or Maslow's high-frequency words,
these words have not been used in conjunction with
machine learning methods to model consumer needs.
This identifies a theoretical gap where the application
of CLT in consumer behavior research, combined
with advanced computational techniques, can
increase the depth of consumer demand models.
3 METHOD
Using online retail data and psychographic labels, I
will categorize products and brands in this section.
My approach is to use Maslow's Hierarchy of Needs
Theory in conjunction with Constructive Level
Theory (CLT) to develop a comprehensive demand
model for each brand that primarily addresses
Maslow's hierarchy of needs.
3.1 Data Preparation
To analyze the relationship between product sales and
consumer needs, sales data from 16 e-commerce
brands were collected, covering the top 30-50 best-
selling products for each, resulting in 600 data points.
This data was processed and labeled according to
Maslow's hierarchy of needs—basic, safety, social,
esteem, and self-actualization—and four CLT
distance metrics: temporal, spatial, social, and
hypothetical.
With the use of automatic keyword matching
technology (see table 1), products or brands were
categorized based on Maslow's needs and CLT
distances, allowing branch and node modeling to take
place.
EMITI 2024 - International Conference on Engineering Management, Information Technology and Intelligence
190
Table 1: Synonyms and keyword matching.
CLT Distance Synonyms
Physiological
Needs
Time Distance: Instant Delivery, 24/7
Service
Space Distance: Locally Produced,
Local Supply Chain
Social Distance: Group Buying Offers,
Family Packages
Hypothetical Distance: Product Quality
Guarantees, Satisfaction Refunds
Safety Needs
Time Distance: Extended Warranties,
Ongoing Maintenance Services
Space Distance: Safety-Certified
Products, Traceability Systems
Social Distance: User Safety Ratings,
Trusted Seller Badges
Hypothetical Distance: Insurance
Services, Risk Alerts
Social Needs
Time Distance: Seasonal Social Events,
Holiday Sales
Space Distance: Community Stores,
Social Media Interactions
Social Distance: User Groups, Social
Sharing Rewards
Hypothetical Distance: Influencer
Endorsements, Customer Testimonials
Esteem
Needs
Time Distance: Limited Edition
Products, Loyalty Reward Programs
Space Distance: Exclusive
Merchandise, Customization Services
Social Distance: Brand Membership
Privileges, User Rating Systems
Hypothetical Distance: Excellence
Service Certifications, Elite User Groups
Self-
Actualization
Needs
Time Distance: Personal Development
Courses, Creative Workshops
Space Distance: Global Creative
Marketplaces, International Cultural
Products
Social Distance: Creator Communities,
Artist Live Sessions
Hypothetical Distance: Self-Expression
Tools, Inspiration-Triggering Products
3.2 Demand Model
Using Maslow's five hierarchies of needs as nodes,
the model is represented as a node-and-branch
diagram (see Figure 2). These need nodes are
interconnected through specific links, known as
"branches", and each branch describes the
physiological distance associated with a product
through the four characteristics of CLT.
With CLT features, this model maps the dynamic
relationship between needs and assesses the degree of
connection between products and needs. For
example, how a product meets a user's security needs
through its functionality and features, while at the
same time adapting to the consumer's social needs in
time and space. By analyzing these connections and
distances in detail, we can gain insights into how a
product "moves" or evolves between different levels
of needs.
3.3 Result
The categorization of brands into clusters according
to how they satisfy these needs and their respective
CLT distances provides an insightful approach to
analyze brand market. Particularly, Cluster 1 (see
Figure 1), featuring brands like Xiaomi and
Lululemon, showcases an extensive coverage of
Maslow’s demands, each paired with a unique CLT
distance feature. It's notable how these brands span all
five of Maslow's demands (see Figure 2), suggesting
a comprehensive strategy to meet diverse consumer
needs.
The additional observations from Cluster 1 align
with the principles of CLT. By minimizing
hypothetical and temporal distances, these brands
help consumers more vividly imagine using their
products in the near future. Detailed presentations
enable a clearer and more immediate vision of
product use, fostering a sense of proximity and
tangibility.
In addition, the study emphasizes the value of
reducing spatial and hypothetical distances. Many of
these brands categorized as Cluster1 have their own
offline physical stores. By providing a direct product
experience, these brands are able to reduce spatial
distance, thereby enhancing the tangibility and
credibility of their products. These factors greatly
influence consumer trust and confidence, which is
crucial for an in-person shopping experience.
Through the presence of a physical store, brands are
able to not only provide an opportunity to physically
touch and feel the product, but also enhance
consumers' willingness to buy through direct human
interaction and immediate service feedback.
Construal Level Theory and Maslow’s Hierarchy with Machine Learning for Enhanced Consumer Demand Analysis
191
Figure 1: Brand Clustering Visulization.
Figure 2: Demand Model.
4 CONCLUSION
4.1 Summary
In this study, we constructed a graph that reflects the
aggregation of similar brands. This analysis initially
involved labeling the data according to Maslow's
hierarchy of needs, which are satisfied by the
products, and proceeded with additional labeling and
clustering in relation to the psychological distances—
such as temporal, spatial, and social distances—
outlined in Construal Level Theory (CLT). This
methodology allows us to uncover how various
brands meet distinct consumer needs and deepen our
understanding of brand positioning in terms of
consumers' perception of psychological distance.
Drawing on insights from existing literature and
leveraging recent advancements in Clustering, this
research demonstrates the effective combination of
CLT with Maslow's Hierarchy of Needs theory. As a
result of aligning products and services with
Maslow's hierarchy and psychological labels
provided by CLT, we enable an accurate assessment
of consumer needs, which benefits consumers as well
as third parties in achieving their strategic goals.
4.2 Recommandations and Future
Agenda
Based on the insights derived from combining
Construal Level Theory (CLT) and Maslow's
Hierarchy of Needs Theory with machine learning
models, future research could utilize more
sophisticated techniques such as Graphical Neural
Networks (GNNs) to enhance the personalization and
effectiveness of customer experience strategies. As
described by Posner and Rothbart (2007), neural
networks mimic the functioning of brain regions that
work together to perform complex psychological and
physiological functions. GNNs are very similar to the
model presented in this article, and this analogy
extends to how neural networks interact in a dynamic,
nonlinear manner that may not be captured by
traditional models to synthesize and process
consumer needs Modeling.
As highlighted by Perez-Vega et al. (2021), there
are high expectations for AI systems to personalize
EMITI 2024 - International Conference on Engineering Management, Information Technology and Intelligence
192
the customer experience and improve marketing
outcomes through active and inactive forms of
customer engagement. Combining GNN with this
model can enhance the ability of these systems to
provide real-time, context-aware personalization that
psychologically satisfies consumers' individual
needs.
REFERENCES
Belk, Russell W. (1988) "Property, Persons, and Extended
Sense of Self," Proceedings 0/ the Division 0/
Consumer Psychology, American Psychological
Association 1987 Annual Convention, New York, ed.
Linda F. Alwitt, Washington, D.C.: American
Psychological Association, 28- 33.
British Psychological Society. (2021). What is psychology?
https://www. bps.org.uk/public/what-is-psychology
Ding, Y., Wan, E. W., & Xu, J. (2017). The impact of
identity breadth on consumer preference for advanced
products. Journal of Consumer Psychology, 27, 231–
244. https://doi.org/10.1016/J.JCPS.2016.11.001\
Jastrzebska, A., Homenda, W. (2012). On Structuring of the
Space of Needs in the Framework of Fuzzy Sets
Theory. In: Nguyen, NT., Hoang, K., Jȩdrzejowicz, P.
(eds) Computational Collective Intelligence. Tech-
nologies and Applications. ICCCI 2012. Lecture Notes
in Computer Science, vol 7653. Springer, Berlin,
Heidelberg. https://doi.org/10.1007/978-3-642-34630-
9_16
Jordan, P.W. 1999. Pleasure with Product: Human Factors
for Body, Mind and Soul, In Human Factors in Product
Design: Current Practice and Future Trends. Taylor and
Francis.
Maglio, Sam. (2019). Psychological distance in consumer
psychology: Consequences and antecedents. Consumer
Psychology Review. 3. 10.1002/arcp.1057.
Malter, M. S., Holbrook, M. B., Kahn, B. E., Parker, J. R.,
& Lehmann, D. R. (2020). The past, present, and future
of consumer research. Marketing Letters, 31(2), 137–
149.
Maslow, A. 1970. Motivation and Personality. New York:
Harper and Row
Mourali, M., & Nagpal, A. (2013). The powerful select, the
powerless reject: Power’s influence in decision
strategies. Journal of Business Research, 66(7), 874–
880. https://doi.org/10.1016/j.jbusres.2011.12.005 of
Psychology, 58(1), 1–23.
Oghenemaro Anuyah, Karla Badillo-Urquiola, and Ronald
Metoyer. 2023. Characterizing the Technology Needs
of Vulnerable Populations for Participation in Research
and Design by Adopting Maslow’s Hierarchy of Needs.
In Proceedings of the 2023 CHI Conference on Human
Factors in Computing Systems (CHI '23). Association
for Computing Machinery, New York, NY, USA,
Article 85, 1–20. https://doi.org/10.1145/3544548.
3581221
PerezVega, R., Kaartemo, V., Lages, C. R., Razavi, N. B.,
& Männistö, J. (2021). Reshaping the contexts of online
customer engagement behavior via artificial
intelligence: A conceptual framework. Journal of
Business Research, 129(5), 902–910
Posner, M. I., & Rothbart, M. K. (2007). Research on
attention networks as
Sartre, Jean-Paul (1943), Being and Nothingness: A
Phenomenological Essay on Ontology, New York:
Philosophical Library.
Sordi, Jefferson & Tomazelli, Joana & Sampaio, Claudio &
Espartel, Lélis. (2022). Construal Level Theory and
Consumer Behavior: A Decade of Studies and New
Research Possibilities. Revista Brasileira de Marketing.
21. 1060. 10.5585/remark.v21i3.16694.
Trope, Y., & Liberman, N. (2010). Construal-level theory
of psychological distance. Psychological Review,
117(2), 440–463. https://doi.org/10.1037/a0018963
Tuan, Yi-Fu-(1980), "The Significance of the Artifact,"
Geographical Review, 70 (4),462-472.
Yarkoni, T., & Westfall, J. (2017). Choosing prediction
over explanation in psychology: Lessons from machine
learning. Perspectives on Psychological Science, 12(6),
1100–1122.
Construal Level Theory and Maslow’s Hierarchy with Machine Learning for Enhanced Consumer Demand Analysis
193