Understanding regional characteristics through crowd preference and confidence mining in P2P accommodation rental service
| Date | 20 November 2017 |
| Pages | 521-541 |
| DOI | https://doi.org/10.1108/LHT-01-2017-0030 |
| Published date | 20 November 2017 |
| Author | Moloud Abdar,Neil Y. Yen |
Understanding regional
characteristics through crowd
preference and confidence
mining in P2P accommodation
rental service
Moloud Abdar and Neil Y. Yen
School of Computer Science and Engineering, The University of Aizu,
Aizu-Wakamatsu, Japan
Abstract
Purpose –This research intends to look at the regional characteristics through an analysis of crowd
preference and confidence, and investigates how regional characteristics are going to affect human beings at
all aspects in a scenario of sharing economy. The purpose of this paper is to introduce an approach to provide
an understandable rating score. Furthermore, the paper aims to find the relationships between different
features classified in this study by using machine learning methods. Furthermore, due to the importance of
performance of methods, the performance of the features is also improved.
Design/methodology/approach –The Rating Matching Rate (RMRate) approach is proposed to provide
score in terms of simplicity and understandability for all features. The relationships between features can be
extracted from accommodation data set using decision tree (DT) algorithms ( J48, HoeffdingTree, and
REPTree). Usability of these methods was evaluated using different metrics. Two techniques,
“ClassBalancer”and “SpreadSubsample,”are applied to improve the performance of algorithms.
Findings –Experimental outcomes using the RMRate approach show that the scores are very easy to
understand. Three property types are very popular almost in all of selected countries in this study
(“apartment”,“house”, and “bed and breakfast”). The findings also indicate that “Entire home/apt”is the most
common room-type and 4.5 and 5 star-rating are the most given star-rating by users. The proposed DT
algorithms can find the relationships between features significantly. In addition, applied CB and SS
techniques could improve the performance of algorithms efficiently.
Originality/value –This study gives precise details about the guests’preferences and hosts’preferences.
The proposed techniques can effectively improve the performance in predicting the behavior of users in
sharing economy. The findings can also help group decision making in P2P platforms efficiently.
Keywords Rating Matching Rate (RMRate), Feature discovery, Sharing economy, Airbnb, Decision tree,
Optimization
Paper type Research paper
1. Introduction
Human behavior analysis, nowadays, has become essential in all fields of study. Human
behavior evokes a specific functional reaction of people or groups of individuals to both
internal and external stimulus. It includes an array of all physical actions as well as
observable emotions related with individuals. The purpose of human behavior analysis is to
understand the meaning behind human actions, which sometimes are, unconscious;
formulate them; and eventually provide support to human beings. Human behavior can be
examined in various situations and in different places on the internet such as social media,
online marketing, etc. Among large number of these behaviors (e.g. individual preference or
crowd preference, altruist and selfish behaviors, behavioral economics, etc.) (Ren et al., 2013;
Abdar and Yen, 2017a, Guthrie, 2017), we can find different hedonic and utilitarian aspects
of shopping (Wood, 2002), crowd preference, and confidence that can be then utilized to
simplify better decision-making process for users. Indeed, its aim is to indicate the useful
Library Hi Tech
Vol. 35 No. 4, 2017
pp. 521-541
© Emerald PublishingLimited
0737-8831
DOI 10.1108/LHT-01-2017-0030
Received 31 January 2017
Revised 20 March 2017
Accepted 30 April 2017
The current issue and full text archive of this journal is available on Emerald Insight at:
www.emeraldinsight.com/0737-8831.htm
521
P2P
accommodation
rental service
information in such a way that serves the purpose of both manufacturers and customers.
These behaviors can be explored through the massive amount of data.
Sharing economy is a new phenomenon and a prompt development in information
technology. Sharing economy allows users to search, choose, and make decision based on
their preferences. We can find out common/uncommon decisions or behaviors after the
study on human behavior on these platforms (e.g. Airbnb, Uber, DiDi, or TaskRabbits).
The findings are helpful for new and/or current users to have better decisions based on
previous individuals’behaviors, experience, and/or their preference. Therefore, we can
provide more information to the users who do not have enough knowledge, background,
and information about goods and services.
Wu et al. (2016) expressedthat trust has a direct effect on humandecision-making process
in sharing economy. Saaty (2008) emphasized that, before starting the process of decision-
making, understanding some cases is helpful such as knowing the problem(s), the aim of
decision, the criteria of the decision, their sub-criteria, stakeholders and groups affected and
the alternative actions to take. This research concentrates on understanding the regional
characteristics through crowd preference and confidence mining in peer-to-peer (P2P)
accommodation rental service. From this way, we are willing to know whether regional
characteristics have a positive impact on the users’decision-making particularly in P2P
accommodation rental service. Indeed, P2P rental accommodation platform is an alternative
form of accommodation which shows the processwhereby an available home owner prepares
their home or an empty room available for strangers to rent for a short period.
1.1 Target issues and contribution
Over the last few years, many researchers have focused on the study of human behaviors,
and most of them have found many implicit correlations among human behaviors. In this
work, we concentrate on human behavior analysis to find some behavioral patterns such as
users’preferences, hedonic and utilitarian aspects of shopping, etc. Pattern recognition
should be considered as a major issue because in this way, some of patterns can be realized
which are more common among individuals. Finding these patterns helps companies to
provide their services according to their customers’needs and/or preferences whereas it
should be noted that without having such patterns, it is not very easy to find the crowd
preference. Understanding of different human behaviors is extremely important due to its
great impact on human decision-making process in the future. Nowadays, online shopping,
such as online reservations, is growing around the world very fast as well as its popularity
has grown extremely. Thus, three main issues are concentrated:
(1) obtaining significant regional characteristics of specific countries;
(2) obtaining understandable rating scales for all features of characteristics; and
(3) obtaining hidden relationship and correlation between features.
1.2 Airbnb as an instance in sharing economy
Airbnb, that offers a common platform for short-term vacation rental between users, is one
of the well-known companies in sharing economy, and we especially take the collected data
set from this platform to conduct our experiment. The current study tries to figure out which
human behavior will be examined on data. Airbnb was established in 2008 and quickly
became popular and is widely used in various countries of the world (Quattrone et al., 2016).
That is why we will research on Airbnb due to its popularity and as an instance in the online
sharing economy platform.
There are two typesof active users, i.e. host and guest, on theAirbnb platform. Host shares
idling propertiesto guest who is looking for a place to stay. This researchinvestigates crowd
522
LHT
35,4
To continue reading
Request your trial