IEEE Consumer Electronics Magazine - November/December 2020 - 106

Internet Usage Patterns

social networks and online platforms, gender differences in online behavior still exist.
Situated in the Western Balkans, Montenegro
is a country in transition. Its GDP per capita
amounts to 7495 euros annually, and the average
income is 776 euros per month. According to
2018 data, the unemployment rate is 16.1%.1 The
portion of the total population classified as living
in an urban environment is 66.8%, while the education index is 79.7%.2 The share of the population that is female has declined slightly from
50.86% in 2006 to 50.6% today.2 Culturally rooted
gender differences in Montenegro have recently
led to a common practice of artificially controlling gender at birth. In Montenegrin history,
women were usually uneducated, stay-at-home
figures who took care of the family. Often, a Montenegrin man is still imagined as a warrior who
receives an education and "brings home the
bacon." A Montenegrin woman was particularly
valued if she gave birth to sons. Today, the situation is changing. In general, men and women are
educated and employed almost equally. The
human development index for females is 0.794
and for males 0.831; the total unemployment
female-to-male ratio is 0.92.2 However, men still
get better jobs, and the estimated gross national
income per capita for males is 37.3% higher than
for females.2 A male heir is still considered the
greatest family blessing. Internet penetration in
Montenegro is around 70%, less than the European average (89%) but higher than the world
average (57%).3 When it comes to professional
use of the Internet, Montenegro lags behind
developed countries, but this is not the case
when it comes to the use of social networks.
One of the goals of this article is to examine
whether differences exist in the respective
behaviors of male and female Internet users, in
the context of the specific sociocultural and economic conditions of the Montenegrin social community, and to determine the scope of such
differences when detected.
In the early stages of Internet development,
research demonstrated a greater and more
intensive usage of the Internet by men than
women 4 and highlighted that difference in Internet usage between Internet users by gender was
a major factor in online behavior 5 with a focus
on mediated communication. More recent

106

studies continue to confirm gender differences
in the use of social networks,6,7 or multimedia
technologies for learning.8
Internet usage patterns and gender differences have been investigated mainly in the context
of developed countries.9-11 This article seeks to
fill the gap in empirical evidence for countries in
transition, such as Montenegro.
Numerous studies on determining the most
important factors impacting online behavior and
Internet usage patterns identify many variables,
both demographic (e.g., gender, age, education,
income, location, employment, and education
level) and nondemographic (e.g., Internet access at
home, by mobile, or at work, skills, attitudes, motivations, and the digital divide), as well as the diversity of Internet activities.5,10,12 Most studies have
used classical statistical methods, such as confirmatory factor analysis, which involves the a priori
definition of hypotheses to describe the existing
relationships between variables. Deep-learning
methods enable automatic identification of relationships among several variables and show how
such relationships highlight their possible interactions. Such identified interactions shape different
forms of gender-specific Internet-user behavior.
The purpose of this article is to examine
whether deep-learning methods can efficiently
identify the key patterns of Internet usage by
gender. The main goal is to show that the proposed method can generate more objective and
reliable results than the standard statistical
methods used in extant research. Achieving that
goal qualifies this as a pioneer study, the first to
complete research on Internet usage patterns by
gender in this way.

THEORETICAL BACKGROUND
AND RESEARCH MODEL
Theoretical Background
The literature has confirmed gender differences in Internet-use patterns many times. Concerning the adoption and use of ICT technologies,
some analyses show that women tend to display a
more limited use than men of ICT in learning practice,13,14 as well as lower technology acceptance
rates, especially among older people.15 Moreover,
women use the Internet more often as a communication channel, while men use the Internet more

IEEE Consumer Electronics Magazine
IEEE Consumer Electronics Magazine - November/December 2020

Table of Contents for the Digital Edition of IEEE Consumer Electronics Magazine - November/December 2020
