The Use of Intelligent Systems and E-Tourism Applications

NB: We do not resell your papers. Upon ordering, we do an original paper exclusively for you.

NB: All your data is kept safe from the public.

Introduction

Tourism has become a dominant industry not only in the Kingdom of Saudi Arabia but also in other parts of the world. In the past, players in the tourism industry relied on the brick-and-mortar model of operation to manage their businesses. It meant that a customer had to make physical visits to the preferred hotels or use agents to book for various services they need. However, the strategy is changing because of the emerging technologies.

E-tourism has redefined the approach that firms take to operate in the market. Customers can now visit websites of various firms offering services they need, compare the quality of the products they provide, prices they charge, and then make a decision about whether it is appropriate to purchase the services they need from a particular company. Service providers have also benefited from these new technologies. As Gorakala [1] observes, emerging technologies in the field of tourism have eliminated the geographic barrier that limited the scope of their operations.

Competition in the tourism industry is taking a new approach that is heavily dependent on technology. Firms in this industry are keen on ensuring that they attract online guests to their websites. Various website optimization tools have become popular as they prioritize specific online sites when one uses specific key search words. Ricci [2] explains that the concept of intelligent systems have become critical in the industry.

A firm will not only be interested in attracting potential online customers to their websites but will also convince them to purchase various products once they are on the site. As such, it is necessary to understand their needs, financial capacity, and any other details that influence the buyer’s decision-making process. A firm will require advance systems to monitor activities of these potential customers and understand their interests. In this paper, the aim is to provide a comprehensive literature review about the effects of persuasive ubiquitous computing using semantics technologies to promote e-tourism.

Recommender System

Defining the a Recommendation System

A recommendation system, also known as a recommender system, has become popular in the tourism industry. Chedrawy and Abidi define it as “a subclass of information filtering system that seeks to predict the rating or preference a user would give to an item” [3, p. 5]. The website has become the primary repository of information in the modern digital world. Without proper guidance, it may not be easy to have access to the right information when conducting a search. Technology companies such as Google have come up with a rating system that focuses on understanding the exact needs of the user and presenting the most relevant information first.

Marketing companies have borrowed the same concept to help attract online customers to a specific website. User history, cookies, and time scheduling are some of the ways in which a firm can determine the needs and preferences of an online customer. Such information can be used to provide them with a list of what they need every time they conduct a search [3]. As the name suggests, the system recommends a list of items that fit an individual’s needs in the best way possible.

Web and Mobile Recommendation Systems

The concept of web recommender system has become common in the current digital age. According to Chedrawy and Abidi, a web recommender system refers to “adaptive or personalized information retrieval systems, which retrieve or recommend web-based information artifacts such as documents and websites based on the user’s preferences and goals” [3, p. 2]. It means that when a web user searches for information in the internet, this intelligent system processes it to determine what the individual needs, and then provide a list of recommendations that will meet the needs in the best way possible.

The advanced computing system tries to move away from the idea of one size fits all model for web information, to a more individualistic model [2]. It means that when two individuals, one in the United States and the other in the Kingdom of Saudi Arabia, make an online search on a given issue, the results that each will get in terms of prioritization will be different. The intelligent system tries to ensure that each individual gets the most relevant information based on specific socio-economic, political, and personal facts. Figure 1 below shows a web recommender system

*Fig. 1. A schematic web recommender system [3].*

Mobile computing and mobile services are gaining popularity in the tourism sector. A mobile recommendation system makes it possible for an individual to use smartphones or other hand-held devices such as iPads to have access to information needed. These devices can be used to get a map of a given location, to get direction, or to inform the user where he or she can access specific services within a given area [4].

One of the reasons why mobile recommendation system has gain popularity is the device portability. The user can easily move with the device from one location to another and access information what it is needed. The wireless connectivity of these devices is another factor that makes them popular among tourists and business travelers. It means that information can be made available to the users anywhere as long as the device can be connected to the internet remotely. Figure 2 below shows a web recommender system used to identify specific locations within a given area.

*Fig. 2. A map using mobile recommender system [2].*

Recommendation System Functionalities

The recommendation system has numerous applications in various fields. The need to rate needs of an online user and provide a list of recommendations is important when conducting a search. Aggarwal [4] notes that in the entertainment sector, users rely on this intelligent system to have access to the desired songs or movies. One may just have a line of the lyric but not the tittle of the song. The recommender system will use the scanty information provided by the user to identify what is exactly needed.

A list of the items will be given starting with the most relevant to the least. The system has also become useful when looking for online books and journal articles. Using the title of the book, the name of the author, or a chapter can enable a researcher to get the online document needed.

Online dating is another area where the recommendation system has proven to be effective. The dating sites allow an individual to state what he or she desires in a partner in terms of skin color, weight, height, eye color, hair, age, religion, geographic location, and any other relevant demographic factor. The intelligent system then filters through the list to identify individuals who meet the set standards. The concept is gaining rapid popularity in the e-commerce sector.

Recommendation Technique in E-Tourism

Recommendation technique has become a critical tool in e-tourism. The traditional high street tour agents have become irrelevant in the modern society. The middle class, who make a significant majority of tourists in any country, have limited time to waste [5]. They spend most of their time in office trying to achieve career growth. They do not have time to visit the physical offices of various companies offering tour and related services.

The emergence of e-tourism has a major solution to the time problem that both customer and service providers faced. Instead of making a physical visit to the offices of tour agencies or using brokers in this industry, customers can visit online websites of various tour firms to determine which has the products they need. They can compare the quality of services offered, prices they charge, the appropriateness of the location, and any other important factor before making the purchase.

Service providers have also realized that e-tourism offers limitless opportunities that can enhance sustained growth. According to Borràs, Moreno, and Valls [6], when e-tourism emerged, many players in this industry were scared. They did not understand how their business model would fit into this new system. Some of these firms were forced out of the market because of their inability to embrace change. The innovators and early adopters of the new technology benefited a lot as the geographic scope of their market widened exponentially. Previously, they had to rely on clients who could make physical visits to their offices.

However, the online-based model meant that they could serve customers from any part of the world. Gorakala [1] says that within the next few years, e-tourism will completely eliminate the traditional the brick-and-mortar model of operation in this industry. Figure 3 below shows knowledge-based domain architecture for e-tourism. It identifies most of the important key words that a tourist would use when trying to determine the firm that offers the most appropriate service in the market.

*Fig. 3. A knowledge-based domain for e-tourism [5].*

Type of Recommendation

It is important to understand the different types of recommender systems, which are in wide application. According to Gorakala [1], various ways exist, which can make it possible to list different items that fit the taste of a given individual. When trying to fulfill user requirement, one can use recommender system based on history, cookies, or scheduling based on specific factors. It is necessary to look at each of them to determine when it would be appropriate to use one and not the other two.

Recommender System Based on User History

One of the best types of recommender system is to rely on user history. According to Chedrawy and Abidi [3], this method requires a user to create an account and register specific details. The first time user will state his or her gender, location, preferences, and any other relevant detail. It makes it easy to profile such a customer. People tend to purchase same products every time they want to visit a given place, especially if the previous event was positively memorable [1].

The account owners are often advised to rate their experience based on the services offered to them. A firm can easily review the account of such a customer to understand specific needs that would satisfy them when purchasing tour-related products. User-history recommender system may take different approach. The most popular one is user profiling. In this approach, information about a specific user is gathered directly from their account.

These facts are kept to enable the firm to understand the changing market trends. Other strategies include historical knowledge base approach, data processing, tourism knowledge base, and ranking [2]. The choice of the approach depends on the specific information that a researcher needs.

Recommender System Based on Cookies

When providing information to non-registered users, it is necessary to use cookies to determine what they need. According to Chedrawy and Abidi [3], reading cookies involves checking cookies stored in the user’s system to get history of the popular visits. The assumption that is made is that people often visit websites that they believe offer the information they need. The sites they frequently visit and the constant searches they make will help determine their preferences.

Reading cookies is effective when dealing with random visitors in a given website. Gorakala [1] warns that one of the main weaknesses of this approach is that sometimes people use devices that do not belong to them. One may borrow a friend’s computer or phone to make an inquiry about a given product with the aim of purchasing it. It means that the information that will be used belong to another person. As such, it is possible to provide a misleading recommendation to the user. In other cases, there may not be any cookies to rely on, especially when using a new device or when the cookies have been cleared. Having proper guidance in such cases may not be easy.

Recommender System Based on Time Scheduling

The third recommender system is based on time scheduling. In this case, the focus is based on the time that a search is made. For instance, when the search is made during the month of Ramadan, the recommender system will focus on issues related to this period of fasting, especially if the search is made in a region that is dominated by Muslims such as Saudi Arabia. If it made during or when approaching Eid al-Fitr, the outcome of the search will be related to this event.

Tourists have been using this approach to recommend services that they can offer to their customers during specific period. The cities of Mecca and Medina are holy cities that are often visited by people from all over the world.

Whenever one makes a search during holy months when people are expected to make pilgrimage to these holy cities, the local tour firms will be quick to provide a detailed recommendation of what they can offer. The product offered must be specific in meeting the needs of these visitors.

Table 1 below shows a typical recommender of a visitor who may want to visit the city of Dehradun in India for leisure and religious purposes. It is evident that the information goes beyond offering the specific products that the firm offers. It goes a step further to outline activities that the tourists can conduct places where to get various additional services, and when to visit the Buddha temple in case it is necessary. Such detailed information makes it easy for the client to schedule various activities after making the visit.

*Table 1. Schedule webpage developed using scheduling algorithm [5].*

Representation of User Profile

User profile was identified as one of the easiest ways of determining the needs of a customer in the tourism industry. Firms in this industry currently encourage their clients to develop user accounts. The profile of these customers provides critical information about them that can help in predicting their preferences. Age, gender, income, religion, physical address, family size, preferred destinations, and time when one takes holidays are some of the factors that are often captured in the profile.

When this information is made available in the intelligent system, it is easy to provide these customers with recommended items that meet their needs in the best way possible. The system will ensure that the recommendations made take into consideration the financial capacity of the client, personal and family needs, and any other relevant fact. Users are often encouraged to update their profile based on changes that may occur from time to time.

Issues about marital status, size of the family, religion, and personal/family preferences can change. Allowing them to update the user profile makes it easy to understand if it is necessary to adjust products that a firm offers to its clients in the market because of changing trends and practices.

Intelligent Systems

The recommender system has been widely described as an intelligent system [3]. The emerging technologies are making life easier. In the tourism sector, it has redefined the approach that players use to operate in the market. It is no longer possible for a firm to use the traditional model of operation and still achieve success. In this section of the report, the researcher will explain why the system is viewed as being intelligence and how it is applied in the tourism sector and other related field.

What Makes Intelligent Systems Intelligent

It is necessary to start by explaining what makes the recommender system intelligent. Agarwal, Sharma, Kumar, Parshav, Srivastava, and Goudar explain that the recommender systems “can analyses the behavior of a user, learn automatically the user profile and provide proactive recommendations depending on the current context” [5, p. 411]. Intelligence is a characteristic that is often associated with human being. The ability to gather facts, analyze them, and come up with an appropriate decision is a sign of intelligence that is often unique to human beings. However, the recommender system is proving to have the same characteristics.

It has the capacity to profile an individual based on specific characteristics and present information that such a specific individual needs at a given time. For instance, when a person is traveling to Mecca for the first time, the recommender system can provide a detailed plan of the activities that such a person should carry out and address concerns and fears that he or she would have while in the country. The fact that the system provides the information in an independent way without a direct control of a person makes it intelligent. This level of intelligence is what has made it popular in the tourism industry.

The Role of Intelligent Systems in Tourism Recommender Systems

The intelligent system has become critical in the tourism recommender system. According to Chedrawy and Abidi [3], it is estimated that about 6 billion people are regular users of mobile phones. The study also shows that over 95% of those who travel for leisure or for business reasons are active users of hand-held devices. In a market where competition is very stiff, understanding customer needs is one of the most important factors that define the ability of a firm to achieve sustainable success.

The use of the intelligent system has become critical in providing the information that firms need to ensure that they not only understand the changing market trends but also help customers to get what they need with ease. As Aggarwal [4] explains, customers may not know what to expect when visiting a place for the first time. The ability of the recommender system to come up with a detailed plan of the activities that one should carry out based on their specified needs can be helpful to the tourists. It will be a sign that the firm is able to provide solutions to the issues the client has. Successful tourism firms are heavily relying on these systems to ensure that they have pools of loyal customers.

Multi-Agent Systems

Agents in the tourism industry sometimes need to coordinate to ensure that they achieve common goals in the market. Borràs, Moreno, and Valls define multi-agent systems as “groups of agents that communicate between themselves to share information and resources, coordinate their activities, and cooperate in the joint efficient solution of a distributed problem” [6, p. 7381]. Agents operating within a given geographic area may experience similar problems.

In other cases, they may offer complimentary products. As such, they need to maintain close coordination to help them realize common objectives. They need a system that makes it easy to share data in a seamless way. Having a common database accessible to each member of the system is critical. An agent can provide recommendations to his client about another agent that can offer other needs. The system seeks to promote communal development.

Optimization Technique

Tourism recommender system is expected to solve complex problems in the industry. However, sometimes even the intelligent system may have difficulty in finding the exact solution to the given issue. The optimization technique helps in determining the optimum solution in a given context. Finding the unconstrained minima and maxima of a continuous differentiable function may help to predict the optimal solution [1].

The use of differential calculus to locate optimum points in a given situation is a more practical and scientific approach to solving problems that may be encountered by travel agents. This technique can offer guidance on the appropriate approach that should be taken when encountering a new challenge that lacks a clear solution. It reduces the possibility of making critical mistakes that may have devastating consequences to a firm. Tourism industry is very sensitive. Customers want to have fun, and when the services offered to them fail to meet their expectations, they would easily consider moving to other rival firms hoping to find what they desire.

Automatic Clustering

Most of the cluster analysis techniques often rely on prior knowledge of data sets to perform clustering, and they are often affected by outlier points and noise [4]. However, the automatic clustering technique can under these clustering tasks even if it lacks prior knowledge of the data sets [2]. The algorithm is by outlier points or noise. This advanced system is becoming useful among tour agents. Sometimes various forces may affect data. This automatic system makes it possible to undertake these activities even in situations where other factors may influence the ability to obtain optimal solution. It gives assurance to its users that the predictions made will be accurate despite the possible factors that may affect the industry.

Knowledge Representation

Knowledge representation is an aspect of artificial intelligence that is dedicated to the representation of information in a form that a computer system can use to solve complex problems [3]. In e-tourism, the use of ontologies is becoming a popular way of representing domain knowledge [6]. Many tourism recommenders are currently using ontologies in formalizing their domain knowledge. It allows them to have specific information about a client, such as accommodation needed, the preferred restaurant, transport services that should be offered, shopping practices, and cultural forces [1]. Having the demographic information of a tourist will guide in determine the optimal solution when trying to address their needs.

Management of Uncertainty

Recommending appropriate activities to tourists based on the perceived traits and characteristics can be very challenging. As Gorakala [1] notes, it is not easy to determine the precise relationship between the observed characteristics and preferences of a tourist. It is common to find cases where people who share many characteristics have different preferences. As such, it is common to make recommendations to a customer that fails to focus on specific desires.

Approximate reasoning is an aspect of Al that seeks to explain this uncertain relationship. Aggarwal [4] notes that Bayesian networks have been developed to manage such uncertainties. The cyclic graphs are used to explain the possible relationships of casualty as a way of dealing with the uncertainties. The goal is to ensure that possible cases of variations in preferences are captured to determine the optimal plan of activities for every tourist.

Critical Issues in Designing and Evaluating Intelligent System

Tourism industry has become heavily dependent on intelligence system. However, designing and evaluating such a system may be affected by various challenges. One of the challenges often encounter in the design stage is the ability to understand the exact preferences of different people having varied needs [1]. The system will always perform tasks based on how it was designed. If the designer ignored specific issues about a section of the market, the system will not meet needs of that section.

It is not advisable to trust a system that lacks the capacity to undertake specific tasks. When it comes to the evaluation of the system, Chedrawy and Abidi [3] argue that the person conducting the assessment must understand the design of the system and current facts in the market. The knowledge will help in determining whether the system is accurate with its prediction. However, sometimes the assessor may have design knowledge but lack the relevant market facts that would make it possible to evaluate the system effectively.

Related Work

When discussing the use of intelligence systems and e-tourism recommender application, it is equally important to look at ways in which extremists are using the same concepts to achieve their selfish goals. According to Chedrawy and Abidi [3], security is one of the most important factors that influence the growth of tourism within a given region. Tourists want to feel safe. When they feel threatened, they can cancel their planned travel or consider moving to safe destinations in other parts of the world. Some criminals and extremists are currently using sophisticated technologies that pose a serious threat to national security. Hacking is a serious problem common in this industry. Players need to come together and find ways of addressing these challenges.

Discussion

The recommender system has become an important tool that tour companies are using to help their clients plan their activities based on their preferences. It involves acquiring, processing, and making sense out of digital data to predict the best way of offering needed services to customers. Aggarwal [4] argues that developing an appropriate schedule for a tourist is the ultimate sign that a firm has a proper understanding of preferences of the client. Although the intelligent system often develop an appropriate plan, in some cases mistakes to occur. As such, Chedrawy and Abidi [3] suggest that it may be appropriate to have measures that can deal with such inconsistencies.

There is room for improvement as tourism continues to become a major aspect of the economy in different parts of the world. Characteristics of a middle class in the United States may be different from that in the Kingdom of Saudi Arabia based on the socio-economic and political differences between the two countries. These facts need to be captured by this system.

Conclusion

Tourism is one of the rapidly growing industries in the Kingdom of Saudi Arabia and various other parts of the world. Tour companies are moving away from the traditional the brick-and-mortar model of business to e-tourism. Technology has become a critical tool in facilitating various activities in the industry. Intelligent tourism recommender system is one of the aspects of technology that has emerged to make the experience of visitors more memorable. It makes it possible to predict preferences of customers based on specific demographical characteristics. Although the system may need some improvement, it has become a popular tool of scheduling activities of visitors in the country.

Reference List

S. Gorakala, Building Recommendation Engines. Birmingham, UK: Birmingham Packt Publishing, 2016.
F. Ricci, “Mobile recommender systems,” Information Technology & Tourism, vol. 12, no. 3, pp. 205-231. 2011. Web.
Z. Chedrawy and S. Abidi, “A web recommender system for recommending, predicting and personalizing music playlists,” In Proc. the Faculty of Computer Science 1, 2009, pp. 335-342.
C. Aggarwal, Recommender Systems: The Textbook. New York, NY: Springer, 2016.
J. Agarwal, N. Sharma, P. Kumar, V. Parshav, A. Srivastava, and R. Goudar, “Intelligent search in e-tourism services using recommendation system: Perfect guide for tourist,” In Prec. Proceedings of 7th International Conference on Intelligent Systems and Control 978, 2013, pp. 411-415.
J. Borràs, A. Moreno and A. Valls, “Intelligent tourism recommender systems: A survey,” Expert Systems with Applications, vol. 41, no. 1, pp. 7370–7389, 2014.

Click Here To Order Now!