Integrating collaborative filtering and search-based techniques for personalized online product recommendation

The existing Collaborative Filtering (CF) technique that has been widely applied by e-commerce sites requires a large amount of ratings data to make meaningful recommendations. It is not directly applicable for recommending products that are not frequently purchased by users, such as cars and houses, as it is difficult to collect rating data for such products from the users. Many of the e-commerce sites for infrequently purchased products are still using basic search-based techniques whereby the products that match with the attributes given in the target user's query are retrieved and recommended to the user. However, search-based recommenders cannot provide personalized recommendations. For different users, the recommendations will be the same if they provide the same query regardless of any difference in their online navigation behaviour. This paper proposes to integrate collaborative filtering and search-based techniques to provide personalized recommendations for infrequently purchased products. Two different techniques are proposed, namely CFRRobin and CFAg Query. Instead of using the target user's query to search for products as normal search based systems do, the CFRRobin technique uses the products in which the target user's neighbours have shown interest as queries to retrieve relevant products, and then recommends to the target user a list of products by merging and ranking the returned products using the Round Robin method. The CFAg Query technique uses the products that the user's neighbours have shown interest in to derive an aggregated query, which is then used to retrieve products to recommend to the target user. Experiments conducted on a real e-commerce dataset show that both the proposed techniques CFRRobin and CFAg Query perform better than the standard Collaborative Filtering (CF) and the Basic Search (BS) approaches, which are widely applied by the current e-commerce applications. The CFRRobin and CFAg Query approaches also outperform the e- isting query expansion (QE) technique that was proposed for recommending infrequently purchased products.

Its place in property education : where does property law fit into property programs?

Property law is one of the key elements in any property-based degree program. In particular, an understanding of 'property law' is one of the required knowledge fields for inclusion in property programs accredited by professional institutes such as the Royal Institution of Chartered Surveyors, the Appraisal Institute and the Australian Property Institute. Despite the importance of property law as a cornerstone element of all property programs this aspect of the program is often approached from a more generic legal perspective with teaching resources used and pedagogical approach more aligned to the study of law that property. The specificity of this type of program is rarely adequately acknowledged. The question arises as to what the study of 'property law' entails and what the composition of a 'property law' subject should be. Replicating the methodology used by Placid and Weeks (2009) in their examination of the current composition of real estate law courses in the United States, this paper examines the current composition and pedagogical approach adopted by Australian universities based on the study of three Queensland property programs. In particular the curriculum, teaching resources used, assessment and engagement strategies are considered with a view to making improvements to the way these property law courses can be more effectively tailored to property students. It is anticipated that the outcomes of this paper will be of interest to all academics who are responsible for developing and delivering property law subjects and those who manage property programs in Australia and internationally.

Reviewing the impact of the 2008/2009 global financial crisis (GFC) on international property markets and property professions

The global financial crisis that impacted on all world economies throughout 2008 and 2009. This impact has not been confined to the finance industries but has had a direct and indirect impact on the property industry worldwide from both an ownership and investment perspective. Property markets have experienced various levels of impact from this event, but universally the greatest impact has been on the traditional commercial and industrial property sectors from the investor perspective, with investment and superannuation funds reporting significant declines in the reported value of these investments. Despite the very direct impact of these declining property markets, the GFC has also had a very significant indirect impact on the various property professions and how these professions are now operating in this declining property market. Of particular interest is the comparison of the property market forecasts in late 2007 to the actual results in 2008/2009.

Analyzing the literature for the link between the conservative Islamic culture of Saudi Arabia and the design of sustainable housing

Saudi Arabia experiences housing shortage for mid and low-income families, which is caused by rapid population growth. This condition is worsened by the fact that the current housing supply has problems in meeting both sustainable requirements and cultural needs of those families. This paper aims to investigate the link between the unique conservative Saudi culture and the design of sustainable housing, while keeping the housing cost affordable for mid and low-income families. The paper is based on a review of literatures on the issues of the Islamic culture and how can they be integrated into the design process of a Saudi house. Findings from literature reveiw suggest several design requirements for accommodating the conservative Saudi Culture in low cost sustainable houses. Such requirements include the implementation of proper usage of windows, and house orientation with a courtyard inside rather than facing the main street will provide natural ventilation while maintaining privacy. The main contribution to the body of knowledge is that this is a new approach to sustainable housing in Saudi Arabia considering not only energy use and architectural design issues but also socio-cultural issues as an essential part of sustainability.

Risky driving behavior among university students and staff in the Sultanate of Oman

Background: There is a well developed literature on research investigating the relationship between various driving behaviours and road crash involvement. However, this research has predominantly been conducted in developed economies dominated by western types of cultural environments. To date no research has been published that has empirically investigated this relationship within the context of the emerging economies such as Oman. Objective: The present study aims to investigate driving behaviour as indexed in the Driving Behaviour Questionnaire (DBQ) among a group of Omani university students and staff. Methods: A convenience non-probability self- selection sampling approach was utilized with Omani university students and staff. Results: A total of 1003 Omani students (n= 632) and staff (n=371) participated in the survey. Factor analysis of the BDQ revealed four main factors that were errors, speeding violation, lapses and aggressive violation. In the multivariate logistic backward regression analysis, the following factors were identified as significant predictors of being involved in causing at least one crash: driving experience, history of offences and two DBQ components i.e. errors and aggressive violation. Conclusion: This study indicates that errors and aggressive violation of the traffic regulations as well as history of having traffic offences are major risk factors for road traffic crashes among the sample. While previous international research has demonstrated that speeding is a primary cause of crashing, in the current context, the results indicate that an array of factors is associated with crashes. Further research using more rigorous methodology is warranted to inform the development of road safety countermeasures in Oman that improves overall traffic safety culture.

Integrating collaborative filtering and matching-based search for product recommendation

Currently, recommender systems (RS) have been widely applied in many commercial e-commerce sites to help users deal with the information overload problem. Recommender systems provide personalized recommendations to users and thus help them in making good decisions about which product to buy from the vast number of product choices available to them. Many of the current recommender systems are developed for simple and frequently purchased products like books and videos, by using collaborative-filtering and content-based recommender system approaches. These approaches are not suitable for recommending luxurious and infrequently purchased products as they rely on a large amount of ratings data that is not usually available for such products. This research aims to explore novel approaches for recommending infrequently purchased products by exploiting user generated content such as user reviews and product click streams data. From reviews on products given by the previous users, association rules between product attributes are extracted using an association rule mining technique. Furthermore, from product click streams data, user profiles are generated using the proposed user profiling approach. Two recommendation approaches are proposed based on the knowledge extracted from these resources. The first approach is developed by formulating a new query from the initial query given by the target user, by expanding the query with the suitable association rules. In the second approach, a collaborative-filtering recommender system and search-based approaches are integrated within a hybrid system. In this hybrid system, user profiles are used to find the target user’s neighbour and the subsequent products viewed by them are then used to search for other relevant products. Experiments have been conducted on a real world dataset collected from one of the online car sale companies in Australia to evaluate the effectiveness of the proposed recommendation approaches. The experiment results show that user profiles generated from user click stream data and association rules generated from user reviews can improve recommendation accuracy. In addition, the experiment results also prove that the proposed query expansion and the hybrid collaborative filtering and search-based approaches perform better than the baseline approaches. Integrating the collaborative-filtering and search-based approaches has been challenging as this strategy has not been widely explored so far especially for recommending infrequently purchased products. Therefore, this research will provide a theoretical contribution to the recommender system field as a new technique of combining collaborative-filtering and search-based approaches will be developed. This research also contributes to a development of a new query expansion technique for infrequently purchased products recommendation. This research will also provide a practical contribution to the development of a prototype system for recommending cars.

Attitudes of future special education teachers toward gifted students and their education

Saudi Arabian education is undergoing substantial reform in the context of a nation transitioning from a resource-rich economy to a knowledge economy. Gifted students are important human resources for such developing countries. However, there are some concerns emanating from the international literature that gifted students have been neglected in many schools due to teachers’ attitudes toward them. The literature shows that future teachers also hold similar negative attitudes, especially those in Special Education courses who, as practicing teachers, are often responsible for supporting the gifted education process. The purpose of this study was to explore whether these attitudes are held by future special education teachers in Saudi Arabia, and how the standard gifted education course, delivered as part of their program, impacts on their attitudes toward gifted students. The study was strongly influenced by the Theory of Reasoned Action (Ajzen, 1980, 2012) and the Theory of Personal Knowledge (Polanyi, 1966), which both suggest that attitudes are related to people’s (i.e. teachers’) beliefs. A mixed methods design was used to collect quantitative and qualitative data from a cohort of students enrolled in a teacher education program at a Saudi Arabian university. The program was designed for students majoring in special education. The quantitative component of the study involved an investigation of a cohort of future special education teachers taking a semester-long course in gifted education. The data were primarily sourced from a standard questionnaire instrument modified in the Arabic language, and supplemented with questions that probed the future teachers’ attitudes toward gifted children. The participants, 90 special education future teachers, were enrolled in an introductory course about gifted education. The questionnaire contained 34 items from the "Opinions about the Gifted and Their Education" (Gagné, 1991) questionnaire, utilising a five-point Likert scale. The quantitative data were analysed through the use of descriptive statistics, Spearman correlation Coefficients, Paired Samples t-test, and Multiple Linear Regression. The qualitative component focussed on eight participants enrolled in the gifted education course. The primary source of the qualitative data was informed by individual semi-structured interviews with each of these participants. The findings, based on both the quantitative and qualitative data, indicated that the majority of future special education teachers held, overall, slightly positive attitudes toward gifted students and their education. However, the participants were resistant to offering special services for the gifted within the regular classroom, even when a comparison was made on equity grounds with disabled students. While the participants held ambivalent attitudes toward ability grouping, their attitudes were positive toward grade acceleration. Further, the majority agreed that gifted students are likely to be rejected by their teachers. Despite such judgments, they considered the gifted to be a valuable resource for Saudi society. Differences within the cohort were found when two variables emerged as potential predictors of attitude: age, experience, and participants’ hometown. The younger (under 25 years old) future special education teachers, with no internship or school practice experience, held more positive attitudes toward the gifted students, with respect to their general needs, than did the older participants with previous school experiences. Additionally, participants from a rural region were more resistant toward gifted education than future teachers from urban areas. The findings also indicated that the attitudes of most of the participants were significantly improved, as a result of the course, toward ability grouping such as special classes and schools, but remained highly concerned about differentiation within regular classrooms with either elitism or time pressure. From the findings, it can be confirmed that a lectured-based course can serve as a starting point from which to focus future teachers’ attention on the varied needs of the gifted, and as a conduit for learning about special services for the gifted. However, by itself, the course appears to have minimal influence on attitudes toward differentiation. As a consequence, there is merit in its redevelopment, and the incorporation of more practical opportunities for future teachers to experience the teaching of the gifted.

Integrating collaborative filtering and matching-based search for product recommendations

Currently, recommender systems (RS) have been widely applied in many commercial e-commerce sites to help users deal with the information overload problem. Recommender systems provide personalized recommendations to users and, thus, help in making good decisions about which product to buy from the vast amount of product choices. Many of the current recommender systems are developed for simple and frequently purchased products like books and videos, by using collaborative-filtering and content-based approaches. These approaches are not directly applicable for recommending infrequently purchased products such as cars and houses as it is difficult to collect a large number of ratings data from users for such products. Many of the ecommerce sites for infrequently purchased products are still using basic search-based techniques whereby the products that match with the attributes given in the target user’s query are retrieved and recommended. However, search-based recommenders cannot provide personalized recommendations. For different users, the recommendations will be the same if they provide the same query regardless of any difference in their interest. In this article, a simple user profiling approach is proposed to generate user’s preferences to product attributes (i.e., user profiles) based on user product click stream data. The user profiles can be used to find similarminded users (i.e., neighbours) accurately. Two recommendation approaches are proposed, namely Round- Robin fusion algorithm (CFRRobin) and Collaborative Filtering-based Aggregated Query algorithm (CFAgQuery), to generate personalized recommendations based on the user profiles. Instead of using the target user’s query to search for products as normal search based systems do, the CFRRobin technique uses the attributes of the products in which the target user’s neighbours have shown interest as queries to retrieve relevant products, and then recommends to the target user a list of products by merging and ranking the returned products using the Round Robin method. The CFAgQuery technique uses the attributes of the products that the user’s neighbours have shown interest in to derive an aggregated query, which is then used to retrieve products to recommend to the target user. Experiments conducted on a real e-commerce dataset show that both the proposed techniques CFRRobin and CFAgQuery perform better than the standard Collaborative Filtering and the Basic Search approaches, which are widely applied by the current e-commerce applications.

Prevalence of depressive symptoms as elicited by Patient Health Questionnaire (PHQ-9) among medical trainees in Oman

Background Despite the increasing recognition that medical training tends to coincide with markedly high levels of stress and distress, there is a dearth of validated measures that are capable of gauging the prevalence of depressive symptoms among medical residents in the Arab/Islamic part of the world. Objective The aim of the present study is two-fold. First is to examine the diagnostic validity of the Patient Health Questionnaire (PHQ-9) using an Omani medical resident population in order to establish a cut-off point. Second is to compare gender, age, and residency level among Omani Medical residents who report current depressive symptomatology versus those who report as non-depressed according to PHQ-9 cut-off threshold. Results A total of 132 residents (42 males and 90 females) consented to participate in this study. The cut-off score of 12 on the PHQ-9 revealed a sensitivity of 80.6% and a specificity of 94.0%. The rate of depression, as elicited by PHQ-9, was 11.4%. The role of gender, age, and residency level was not significant in endorsing depression. Conclusion This study indicated that PHQ-9 is a reliable measure among this cross-cultural population. More studies employing robust methodology are needed to confirm this finding.

A data mining approach to improve the automated quality of data

This thesis describes the development of a robust and novel prototype to address the data quality problems that relate to the dimension of outlier data. It thoroughly investigates the associated problems with regards to detecting, assessing and determining the severity of the problem of outlier data; and proposes granule-mining based alternative techniques to significantly improve the effectiveness of mining and assessing outlier data.

Assessing the construct validity and reliability of the parental perception on antibiotics (PAPA) scales

Background: The overuse of antibiotics is becoming an increasing concern. Antibiotic resistance, which increases both the burden of disease, and the cost of health services, is perhaps the most profound impact of antibiotics overuse. Attempts have been made to develop instruments to measure the psychosocial constructs underlying antibiotics use, however, none of these instruments have undergone thorough psychometric validation. This study evaluates the psychometric properties of the Parental Perceptions on Antibiotics (PAPA) scales. The PAPA scales attempt to measure the factors influencing parental use of antibiotics in children. Methods: 1111 parents of children younger than 12 years old were recruited from primary schools’ parental meetings in the Eastern Province of Saudi Arabia from September 2012 to January 2013. The structure of the PAPA instrument was validated using Confirmatory Factor Analysis (CFA) with measurement model fit evaluated using the raw and scaled χ2, Goodness of Fit Index, and Root Mean Square Error of Approximation. Results: A five-factor model was confirmed with the model showing good fit. Constructs in the model include: Knowledge and Beliefs, Behaviors, Sources of information, Adherence, and Awareness about antibiotics resistance. The instrument was shown to have good internal consistency, and good discriminant and convergent validity. Conclusion: The availability of an instrument able to measure the psychosocial factors underlying antibiotics usage allows the risk factors underlying antibiotic use and overuse to now be investigated.

Social engineering in social networking sites : phase-based and source-based models

Social networking sites (SNSs), with their large numbers of users and large information base, seem to be perfect breeding grounds for exploiting the vulnerabilities of people, the weakest link in security. Deceiving, persuading, or influencing people to provide information or to perform an action that will benefit the attacker is known as “social engineering.” While technology-based security has been addressed by research and may be well understood, social engineering is more challenging to understand and manage, especially in new environments such as SNSs, owing to some factors of SNSs that reduce the ability of users to detect the attack and increase the ability of attackers to launch it. This work will contribute to the knowledge of social engineering by presenting the first two conceptual models of social engineering attacks in SNSs. Phase-based and source-based models are presented, along with an intensive and comprehensive overview of different aspects of social engineering threats in SNSs.

Social engineering in social networking sites : affect-based model

While social engineering represents a real and ominous threat to many organizations, companies, governments, and individuals, social networking sites (SNSs), have been identified as among the most common means of social engineering attacks. Owing to factors that reduce the ability of users to detect social engineering tricks and increase the ability of attackers to launch them, SNSs seem to be perfect breeding ground for exploiting the vulnerabilities of people, and the weakest link in security. This work will contribute to the knowledge of social engineering by identifying different entities and subentities that affect social engineering based attacks in SNSs. Moreover, this paper includes an intensive and comprehensive overview of different aspects of social engineering threats in SNSs.

Toward understanding social engineering

There is no doubt that social engineering plays a vital role in compromising most security defenses, and in attacks on people, organizations, companies, or even governments. It is the art of deceiving and tricking people to reveal critical information or to perform an action that benefits the attacker in some way. Fraudulent and deceptive people have been using social engineering traps and tactics using information technology such as e-mails, social networks, web sites, and applications to trick victims into obeying them, accepting threats, and falling victim to various crimes and attacks such as phishing, sexual abuse, financial abuse, identity theft, impersonation, physical crime, and many other forms of attack. Although organizations, researchers, practitioners, and lawyers recognize the severe risk of social engineering-based threats, there is a severe lack of understanding and controlling of such threats. One side of the problem is perhaps the unclear concept of social engineering as well as the complexity of understand human behaviors in behaving toward, approaching, accepting, and failing to recognize threats or the deception behind them. The aim of this paper is to explain the definition of social engineering based on the related theories of the many related disciplines such as psychology, sociology, information technology, marketing, and behaviourism. We hope, by this work, to help researchers, practitioners, lawyers, and other decision makers to get a fuller picture of social engineering and, therefore, to open new directions of collaboration toward detecting and controlling it.

Towards quantitative 3D broadband ultrasound characterisation of breast lesions

This thesis describes the development and scientific validation of a real-time quantitative 3D flat-bed ultrasound scanner. Novel short-time Fourier transform software facilitated broadband ultrasound attenuation maps of a breast phantom, enabling detection and identification of both cystic and solid lesions.