Search results

The purpose of this paper is to propose sentiment annotation at sentence level to reduce information overloading while reading product/service reviews in the internet.

The keyword-based sentiment analysis is applied for highlighting review sentences. An experiment is conducted for demonstrating its effectiveness.

A prototype is built for highlighting tourism review sentences in Chinese with positive or negative sentiment polarity. An experiment results indicates that sentiment annotation can increase information quality and user’s intention to read tourism reviews.

This study has made two major contributions: proposing the approach of adding sentiment annotation at sentence level of review texts for assisting decision-making; validating the relationships among the information quality constructs. However, in this study, sentiment analysis was conducted on a limited corpus; future research may try a larger corpus. Besides, the annotation system was built on the tourism data. Future studies might try to apply to other areas.

If the proposed annotation systems become popular, both tourists and attraction providers would obtain benefits. In this era of smart tourism, tourists could browse through the huge amount of internet information more quickly. Attraction providers could understand what are the strengths and weaknesses of their facilities more easily. The application of this sentiment analysis is possible for other languages, especially for non-spaced languages.

Facing large amounts of data, past researchers were engaged in automatically constructing a compact yet meaningful abstraction of the texts. However, users have different positions and purposes. This study proposes an alternative approach to add sentiment annotation at sentence level for assisting users.

User-centered product designs have been attracting increasing attention, particularly in digital design. In interacting with the design support system, designers may face problems such as changing demands (e.g. unclear demands) and insufficient descriptions of these demands (e.g. data scarcity). The purpose of this paper is to build a design support system prototype for demonstrating the feasibility of meeting the high involvement of users in digital products.

Interactive evolutionary computation is applied.

A prototype of self-design greeting card system (SDGCS) was proposed. It provides professional design layouts, offers users numerous self-design models, and allows nonprofessional users to easily design greeting cards. The results of this study show that users were satisfied with the functionality, usefulness, and ease-of-use of the SDGCS.

This study used digital card design as an example for demonstrating the feasibility of satisfying the unclear needs of uses, enabling users to design a digital card creatively and complete their designs quickly. However, the current system only supports the design of static objects and layout of card. And the evaluation sample size was small, which might affect generalizability of the findings.

In practice, greeting card web operators can image the feasible business models by providing the attraction of self-design functionalities.

In current human-centric marketing era, consumers have begun to request interaction with designers in creating the value of a product. However, very few previous studies have provided support for digital product self-design. This study demonstrated the feasibility of satisfying the needs of self-design.

To explore the relationship between emergent user roles and perceived importance of user requirements in a social‐oriented community.

A field study was designed to uncover hidden online social networks, and to elicit and rate user requirements.

User roles might have an impact on their perceptions of requirements. The study showed that significant differences of perceptual requirements on regulation and links exist across user roles.

Only a small‐sized online community (approximately 300 members) participated in this study. One‐quarter of the population filled out the online survey.

Online community builders should invite a handful of different user roles to participate in the design and evolutionary processes of information systems.

The paper challenges popular views about the design of online communities.

To investigate the relationship between key users (defined as their influence) in “information”, “purchase”, “communication” or “entertainment” networks, and the number of elicited requirements in web‐based information systems (WIS).

A lab experiment was designed and conducted to investigate the relationship between college students' elicited requirements for two WIS cases and their social networks.

The individual centrality in “information” networks has a significant positive relationship with the numbers of elicited “information” requirements and total requirements; however, the individual centrality in other social networks has no significant relationship with the number of the elicited requirements.

The requirements collected from “key users” may account for most requirements, which is similar to the results predicted by Pareto's rule.

The origin of a WIS depends on a few influential users. These key users possess more power than others, and they define not only the “requirements” of the site but also its content or knowledge. The WIS designers may take advantage of this fact.

This paper fills the information requirement elicitation gap, while transferring the conventional IS development experiences to WIS.

Based on past study, three different value constructs, including social value, hedonic value, and epistemic value, were adopted in this study to examine their influence on individual's stickiness to use Facebook. Besides, this paper aims to explore how “trust” affects the personal usage behaviors.

The research model was tested with data from 345 Facebook's users using a web survey. The partial least squares technology was used to test the proposed hypotheses.

Results confirmed that hedonic value served as important value concerns for Facebook users. Besides, considering trust factor, the respondents can be classified into two groups. In the high-trust group, social value and hedonic value produced significant impacts on stickiness. In the low-trust group, the statistical results show that epistemic value and hedonic value had impacts on the stickiness for Facebook web site use, but social value aspect had no significant impact.

The respondents were mainly the subjects that belonged to the young age group in Taiwan. Therefore, it should be cautious to generalize the conclusions to other areas or the elder.

This study results facilitate web site operators and marketing researchers to understand what value factors and trust affect the user stickiness of Facebook. Their marketing plan and application plug-in can be accordingly adjusted.

This study provides positive evidences how value factors affect Facebook stickiness. The paper also proved that high-trust and low-trust people have different value models.

This study aims to investigate insurance policy loan applicant characteristics. Additionally, it reveals the behaviour patterns of heavy users who have applied for at least two loans. A policy loan prediction model is established which is designed to increase loan application rates.

The proposed model is implemented using data‐mining techniques and comprises two mechanisms: a business rule generator and a recommendation mechanism. Two analytical approaches, the C.5 and Apriori algorithm, are employed to analyse the profile and browsing log DBs of insured individuals. The prediction model is verified by actual data from a Taiwanese insurance company.

The data‐mining results reveal that five attributes are ultimately used to establish the prediction model, namely: gender, marketing channel, insurance type, area of policy owner, and assumed interest rate. Additionally, the analytical results also indicate that insured individuals apply for loans as a result of arbitrage inducement. The accuracy of loan applicant prediction can exceed 70 per cent. Finally, some interesting patterns emerge for heavy users, such as the finding that loan applicants are used to applying for loans continuously (loan application repetition is on average two to three times).

Some policy owners who are unfamiliar with the web interface prefer to contact insurance personnel directly to discuss their insurance needs, and thus no browsing records are available for such users. In such cases only the profile could be collected and analysed.

The proposed model enables insurance firms to locate potential loan applicants according to the data‐mining results. As in the illustration scenario in the paper, insurance personnel can contact these potential loan applicants before they submit loan applications to the bank. Additionally, loan‐related information is provided for online insurance users based on their browsing logs. The loan application rate is thus expected to increase, along with interest revenue.

As long as the policy proceeds, the interest income from the policy loan seems to be a good option for extending insurance company operational earnings. Understanding the characteristics of loan applicants will provide helpful information. Besides, the proposed mechanism will be more appropriate to online users, who are unwilling to deal with unwanted information.

The purpose of this study is to investigate the relationship between users' role and users' perception of requirements in a web‐based community of practice.

Online survey and social network analysis were adopted in this study.

The study classified user roles as advisors and two types of regular users (both aware of advisors and not); each type of user demonstrated different sets of requirement perceptions. The findings showed that user roles and the level of user involvement did have a significant effect on users' perceptions of requirements. Advisors paid less attention to the interface, communication and recommendation links than the regular users.

It implies that high involvers (core members) are more appropriate for requirement elicitation, even though high involvers might not be the only candidates for requirements elicitation.

Few articles discuss the relationship between user roles and requirements; therefore, the originality of this study is high.

This research conducted two experiments to understand the performance (correctness and efficiency) of novice database designers, and perceptions of ease of use and preferences of two approaches for modeling relational databases: the semantic‐oriented approach (top‐down, e.g. using the entity‐relationship model) and the logical‐oriented approach (bottom‐up, view decomposition, focusing only on the logical model). The findings indicated that in experiment 1, semantic‐oriented treatments performed better in a complex, written‐text case; logical‐oriented treatments were better in a simple, tabular‐form case. The same situation happened in experiment 2 though the differences were not statistically significant.

Although requirement elicitation is generally acknowledged to be very important in traditional information systems development (ISD), it does not get enough attention in most Web‐based information systems development (WISD). This paper highlighted the difference between ISD and WISD, and proposed a three‐stage model of user requirements elicitation for Web‐based information systems. This model divides the requirements definition into three stages: initial analysis, key user requirements elicitation and regular user responses. Most current WIS design methodologies consider only initial analysis, and neglect actual users’ requirements. Key user input is emphasized in this model, and social network analysis is proposed as a tool for identifying key users. Requirements analysis for WISD is no longer considered a one‐stop step, but is better regarded as a continuous evolving process. Finally, managerial implications are also provided in this paper.

The purpose of this guest editorial is to introduce the papers in this special issue.

A brief introduction about the issue of web‐mining applications in e‐commerce and e‐services is provided, along with a summary of the main contributions of the papers that are included in the special issue.

The value of web‐mining techniques can be enhanced through applying them to real environments such as e‐commerce and e‐services. The research fields of web mining, e‐commerce and e‐services can also be expanded.

An overview of the special issue and related research is provided in this paper.