Search results

Online advertisement brings huge revenue to many websites. There are many types of online advertisement; this paper aims to focus on the online banner ads which are usually placed in a particular news website. The investigated news website adopts a pay-per-ad payment model, where the advertisers are charged when they rent a banner from the website during a particular period. In this payment model, the website needs to ensure that the ad pushed frequency of each ad on the banner is similar. Under such advertisement push rules, an ad-recommendation mechanism considering ad push fairness is required.

The authors proposed a novel ad recommendation method that considers both ad-push fairness and personal interests. The authors take every ad’s exposure time into consideration and investigate users’ three different usage experiences in the website to identify the main factors affecting the interests of users. Online ad recommendation is conducted on the investigated news website.

The results of the experiments show that the proposed approach performs better than the traditional approach. This method can not only enhance the average click rate of all ads in the website but also ensure reasonable fairness of exposure frequency of each ad. The online experiment results demonstrate the effectiveness of this approach.

Existing researches had not considered both the advertisement recommendation and ad-push fairness together. With the proposed novel ad recommendation model, the authors can improve the ad click-through rate of ads with reasonable push fairness. The website provider can thereby increase the commercial value of advertising and user satisfaction.

Most academic libraries provide book recommendation services to enable readers to recommend books to the libraries. To facilitate decision-making in book acquisition, this study aimed to develop a method to determine the ranking of the recommended books based on the recommender network.

The recommender network was conducted to establish relationships among book recommenders and their similar readers by using circulation records. Furthermore, social computing techniques were used to evaluate the degree of representativeness of the recommenders and subsequently applied as a criterion to rank the recommended books. Empirical studies were performed to demonstrate the effectiveness of the proposed ranking system. The Spearman’s correlation coefficients between the proposed ranking system and the ranking obtained using reader circulation statistics were used as performance measure.

The ranking calculated using the proposed ranking mechanism was highly and moderately correlated to the ranking obtained using reader circulation statistics. The ranking of recommended books by the librarians was moderately and poorly correlated to the ranking calculated using reader circulation statistics.

The book recommender can be used to improve the accuracy of book recommendations.

This study is the first that considers the recommender network on library book acquisition. The results also show that the proposed ranking mechanism can facilitate effective book-acquisition decisions in libraries.

The purpose of this paper is to combine basic movie information factors, external factors and review factors, to predict box-office performance and identify the most crucial factor of influence for box-office performance.

Five movie genres and first-week movie reviews found on IMDb were collected. The movie reviews were quantified using sentiment analysis tools SentiStrength and Stanford CoreNLP, in which quantified data were combined with basic movie information and external environment factors to predict movie box-office performance. A movie box-office performance prediction model was then developed using data mining (DM) technologies with M5 model trees (M5P), linear regression (LR) and support vector regression (SVR), after which movie box-office performance predictions were made.

The results of this paper showed that the inclusion of movie reviews generated more accurate prediction results. Concerning movie review-related factors, the one that exhibited the greatest effect on box-office performance was the number of movie reviews made, whereas movie review content only displayed an effect on box-office performance for specific movie genres.

Because this paper collected movie data from the IMDb, the data were limited and primarily consisted of movies released in the USA; data pertaining to less popular movies or those released outside of the USA were, thus, insufficient.

This paper helps to verify whether the consideration of the features extracted from movie reviews can improve the performance of movie box-office.

Through various DM technologies, this paper shows that movie reviews enhanced the accuracy of box-office performance predictions and the content of movie reviews has an effect on box-office performance.

Credit ratings have become one of the primary references for financial institutions to assess credit risk. Conventional credit rating approaches mainly concentrated on two-class classification (i.e. good or bad credit), which lacks adequate precision to perform credit risk evaluations in practice. In addition, most of previous researches directly focussed on employing various data mining techniques, but rare studies discussed the influence of data preprocessing before classifier construction. The paper aims to discuss these issues.

This study considers nine-class classification (i.e. nine credit risk level) to credit rating prediction. For the development of more accurate classifiers, the paper adopts two-stage analysis, which integrates multiple data preprocessing and supervised learning techniques. Specifically, the first stage applies feature selection, data clustering, and data resampling methods to preprocess the data, and then the second stage utilizes several classification techniques and classifier ensembles to construct prediction models.

The results show that Bagging-DT with data resampling method achieves excellent accuracy (82.96 percent), indicating that the proposed two-stage prediction model is better than conventional one-stage models.

Practical implication of this study can lower credit rating expenses and also allow corporations to gain credit rating information instantly.

The purpose of this paper is to focus on examining the research impact of papers written with and without funding. Specifically, the citation analysis method is used to compare the general and funded papers published in two leading international conferences, which are ACM SIGIR and ACM SIGKDD.

The authors investigate the number of general and funded papers to see whether the number of funded papers is larger than the number of general papers. In addition, the total citations and the number of highly cited papers with and without funding are also compared.

The analysis results of ACM SIGIR papers show that in most cases the number of funded papers is larger than the number of general papers. Moreover, the total captions, the average number of citations per paper, and the number of highly cited papers all reveal the superiority of funded papers over general papers. However, the findings are somewhat different for the ACM SIGKDD papers. This may be because ACM SIGIR began much earlier than ACM SIGKDD, which relates to the maturity of the research problems addressed in these two conferences.

The value of this paper is the first attempt at examining the research impact of general and funded research papers by the citation analysis method. The research impact of other research areas can be further investigated by other analysis methods.

Conference publications are an important aspect of research activities. There are generally both oral presentations and poster sessions at large international conferences. One can hypothesise that, for the same conferences, the papers presented in oral sessions should have a higher research impact than the papers presented in poster sessions. However, there has been no related study examining the validity of this hypothesis. In other words, the difference of research impact between papers presented orally or during poster sessions has not been discussed in literature. Therefore, the purpose of this paper is to conduct a citation analysis to compare the research impact of papers presented in oral and poster sessions.

In this paper, data from three leading conferences in the field of computer vision are examined, namely CVPR (2011 and 2012), ICCV (2011) and ECCV (2012). Several types of citation-related statistics are collected, including the number of highly cited papers (i.e. high number of citations) presented in oral and poster sessions, the total citations of both types of papers, the average citations of oral and poster papers, and the average citations of each frequently cited paper of both types.

There are three main findings. First, a larger proportion of highly cited papers are from oral sessions than poster sessions. Second, the average number of citations per paper is larger for those presented in oral sessions than poster sessions. Third, the average number of citations for highly cited papers presented in oral sessions is not necessarily greater than for the ones presented in poster sessions.

The originality of this paper is that it is the first attempt to examine the differences of citation impacts of conference papers presented in oral and poster sessions. The findings of this study will allow future bibliometrics research to further explore this related issue for longer periods and different fields.

Ranking relevant journals is very critical for researchers to choose their publication outlets, which can affect their research performance. In the management information systems (MIS) subject, many related studies conducted surveys as the subjective method for identifying MIS journal rankings. However, very few consider other objective methods, such as journals’ impact factors and h-indexes. The paper aims to discuss these issues.

In this paper, top 50 ranked journals identified by researchers’ perceptions are examined in terms of the correlation to the rankings by their impact factors and h-indexes. Moreover, a hybrid method to combine these different rankings based on Borda count is used to produce new MIS journal rankings.

The results show that there are low correlations between the subjective and objective based MIS journal rankings. In addition, the new MIS journal rankings by the Borda count approach can also be considered for future researches.

The contribution of this paper is to apply the Borda count approach to combine different MIS journal rankings produced by subjective and objective methods. The new MIS journal rankings and previous studies can be complementary to allow researchers to determine the top-ranked journals for their publication outlets.

The purpose of this paper is to analyze the role of four important variables in the development of customer loyalty in mobile commerce. These variables are personal (propensity to use information and communication technologies (ICTs)), transactional (opportunism), and relational (trust and satisfaction).

A broad sample of 1,053 mobile customers in Mexico was studied using the structural equation analysis methodology.

The results offer evidence on how trust and satisfaction can increase loyalty and motivate purchases via mobile devices. In addition, the results show evidence of the indirect effect (mediated through trust) of opportunism, and propensity to use ICTs on loyalty.

Achieving customer satisfaction is revealed as the main strategy enterprises should seek in order to encourage repetitive purchases via mobile devices and customer loyalty. At the same time, companies should consider that the customers most likely to use ICTs, and those who perceive less opportunism can also be very loyal as a result of a higher level of trust when making purchases using mobile devices.

The contributions of this paper are: (1) to analyze the generation of loyalty in mobile commerce using a conceptual model that includes variables of different theoretical perspectives and nature, both positive and negative. (2) To provide empirical evidence from a sample of mobile users who have already bought goods via mobile phone, contributing to prior literature that has focused on analyzing the behavior of mobile phone users who do not make purchases via mobile phones. (3) To study mobile commerce in an emerging market with notable potential for growth (Mexico), which has not been studied at length in previous literature.

El presente trabajo analiza el papel de cuatro importantes variables en el desarrollo de la lealtad de los compradores por móvil. Variables de índole personal (propensión al uso de las TICs), transaccional (oportunismo) y relacional (confianza y satisfacción).

Una amplia muestra de 1053 compradores por móvil en México es analizada mediante la metodología de ecuaciones estructurales.

Los resultados ofrecen evidencia sobre la capacidad de la confianza y la satisfacción para incrementar la lealtad y motivar la compra a través del móvil. Además, se muestra evidencia del efecto indirecto (mediado a través de la confianza) del oportunismo y la propensión al uso de las TICs sobre la lealtad.

La consecución de la satisfacción del comprador se revela como la principal estrategia que deben seguir las empresas que buscan fomentar la repetición de la compra a través del móvil y la confianza de sus actuales compradores. A la par, las empresas deben considerar que los clientes más propensos al uso de las TICs y los que perciben menos oportunismo pueden ser más leales, al aumentar su confianza en la compra por móvil.

Las contribuciones son: (1) Analizar la generación de la lealtad en el comercio móvil utilizando un modelo conceptual que incluye variables de distintas perspectivas teóricas y de naturaleza tanto positiva como negativa. (2) Ofrecer evidencia empírica de una muestra de usuarios de teléfono móvil que ya han comprado por este medio, contribuyendo a la literatura previa que se ha centrado en analizar el comportamiento de los usuarios de teléfono móvil no compradores. (3) Estudiar el comercio móvil en un mercado emergente (México) poco estudiado en la literatura previa y con un notable potencial de crecimiento.

Customer lifetime value (CLV) has received increasing attention in database marketing. Enterprises can retain valuable customers by the correct prediction of valuable customers. In the literature, many data mining and machine learning techniques have been applied to develop CLV models. Specifically, hybrid techniques have shown their superiorities over single techniques. However, it is unknown which hybrid model can perform the best in customer value prediction. Therefore, the purpose of this paper is to compares two types of commonly‐used hybrid models by classification+classification and clustering+classification hybrid approaches, respectively, in terms of customer value prediction.

To construct a hybrid model, multiple techniques are usually combined in a two‐stage manner, in which the first stage is based on either clustering or classification techniques, which can be used to pre‐process the data. Then, the output of the first stage (i.e. the processed data) is used to construct the second stage classifier as the prediction model. Specifically, decision trees, logistic regression, and neural networks are used as the classification techniques and k‐means and self‐organizing maps for the clustering techniques to construct six different hybrid models.

The experimental results over a real case dataset show that the classification+classification hybrid approach performs the best. In particular, combining two‐stage of decision trees provides the highest rate of accuracy (99.73 percent) and lowest rate of Type I/II errors (0.22 percent/0.43 percent).

The contribution of this paper is to demonstrate that hybrid machine learning techniques perform better than single ones. In addition, this paper allows us to find out which hybrid technique performs best in terms of CLV prediction.