Online Recommendations Research Articles

On the motivating impact of price and online recommendations at the point of online purchase

Do online recommendations have the same motivating impact as price at the point of online purchase? The results ( n = 268) of an conjoint study show that: (1) when the price is low or high relatively to market price, it has the strongest impact (positive and negative) on the likelihood of an online purchase of an mp3 player, (2) when the price is average to market price, online recommendation and price are equal in their impact at the point of online purchase, and, (3) the relative impact from price increases when online shopping frequencies increases. The implications these results give are that online retailers should be aware that online recommendations are not as influential as a good offer when consumers purchase electronics online. However, other customer recommendations have a stronger impact on novice online shoppers than towards those consumers that shop more frequently online.

Designing utility-based recommender systems for e-commerce: Evaluation of preference-elicitation methods

Recommender systems are useful in reducing information overload and improving decision making. Utility-based recommender systems provide recommendations based on the computation of the utility of each item for the user. Some utility-elicitation methods have been developed on the basis of multi-attribute utility theory (MAUT) to represent a decision maker’s complete preference. This study investigates whether these utility-based techniques outperform the traditional content-based technique for online recommendations. A laboratory experiment was conducted in two e-commerce contexts to compare the decomposed and holistic utility-based methods, simple multi-attribute rating technique exploiting ranks (SMARTER) and radial basis function network (RBFN), with the content-based method vector space model (VSM) in terms of recommendation accuracy, time expense, and user perceptions. The results demonstrate that the performances of utility-based methods depend on recommendation contexts. Furthermore, this study proposes guidelines for choosing appropriate recommendation methods in different contexts.

Oseltamivir im Wochenbett – Vergleich internationaler Empfehlungen

In the current influenza A (H1N1) pandemia, data on neonatal and maternal Oseltamivir chemoprophylaxis and treatment are limited. Recommendations of national and international health authorities do not compensate for a lack of controlled studies on pharmacokinetics and safety. However, the level of consent may contribute to individual clinical decisions. We have reviewed online recommendations by health authorities in the context of the current literature. Given the limited database, there is a high level of consent among recommendations issued by health authorities regarding treatment with Oseltamivir and breast-feeding. The majority of recommendations do not regard treatment with Oseltamivir as a contraindication to breast-feeding. Antiviral chemoprophylaxis of influenza A (H1N1) infection in preterm infants is not recommended due to the lack of data on its pharmacokinetics and safety. Variable recommendations have been issued regarding the choice of neuraminidase inhibitors in pregnancy. Additional information on the pharmacokinetics and safety of neuraminidase inhibitors for breast-feeding mothers and neonates is essential in order to address potential future pandemics.

A new collaborative filtering metric that improves the behavior of recommender systems

Recommender systems are typically provided as Web 2.0 services and are part of the range of applications that give support to large-scale social networks, enabling on-line recommendations to be made based on the use of networked databases. The operating core of recommender systems is based on the collaborative filtering stage, which, in current user to user recommender processes, usually uses the Pearson correlation metric. In this paper, we present a new metric which combines the numerical information of the votes with independent information from those values, based on the proportions of the common and uncommon votes between each pair of users. Likewise, we define the reasoning and experiments on which the design of the metric is based and the restriction of being applied to recommender systems where the possible range of votes is not greater than 5. In order to demonstrate the superior nature of the proposed metric, we provide the comparative results of a set of experiments based on the MovieLens, FilmAffinity and NetFlix databases. In addition to the traditional levels of accuracy, results are also provided on the metrics’ coverage, the percentage of hits obtained and the precision/recall.

An Laboratory Experiment for Comparing Effectiveness of Three Types of Online Recommendations

The widespread use of Internet accelerates the rapid development of business to customer electronic commerce. To reduce information overload and help their customers to make better purchase decisions, e-commerce websites are beginning to use online recommendations. This paper compares the effectiveness of three types of online recommendations, the personalized recommendation, best sellers, and consumers' reviews, which are widely used in e-commerce. This research used a laboratory experiment combined with a questionnaire. This paper also establishes an integrated model of the facts that influence recommendation effectiveness.

Consumers’ Reliance on Product Information and Recommendations Found in UGC

ABSTRACTIn the time since the advent of the Internet, the influence of online recommendations on consumer decision making has attracted great attention. YouTube and sites with blogging capabilities, such as MySpace and Facebook, are growing rapidly and frequently feature comments about brands and products. These comments, whether positive or negative, represent a form of user-generated content (UGC). Although recent research on peer recommendations considers electronic word of mouth, few studies focus on UGC. Using interviews with 17 participants, this study examines consumers’ opinions of online recommendations embedded in UGC compared with those of producer-generated content.

'You should buy this one!' The influence of online recommendations on product attitudes and choice confidence

We use a laboratory experiment to examine the effects of electronic Word-of-Mouth (eWOM) in the form of online customer-to-customer recommendations on attitudes about the recommended product and confidence in the choice decision. Specifically, we manipulate the number of consumer recommendations and measure motivation to process information in a realistic online shopping environment. Consistent with predictions of dual information processing theories, we find that the amount of eWOM has a significant impact on buyer confidence in product choice. In addition, we find that for buyers less motivated to process information, the effect of eWOM on their choice confidence is mediated by their attitude towards the recommended product, suggesting that the amount of eWOM functions as a purchase cue. Our findings have theoretical implications regarding the processes underlying eWOM effectiveness and practical implications for online retailers and policy-makers.

Making sense of credibility on the Web: Models for evaluating online information and recommendations for future research

This article summarizes much of what is known from the communication and information literacy fields about the skills that Internet users need to assess the credibility of online information. The a...

Buzz and Recommendations on the Internet. What Impacts on Box-Office Success?

Potential moviegoers may find information on the Internet on movie critics' recommendations and web users' comments on movies they have seen. The more a recommendation is shared by a large number of individuals, the greater is the buzz. This research explores to what extent this online buzz can be a predictor and/or modifier of box-office results, particularly the week following the launch. A field experiment on 534 movies shows that the buzz, and more specifically critics' recommendations appearing on the allocine.com website, is significantly correlated with box-office results after the first week. Various developments show that these online recommendations may not only predict but also influence box-office results.

Buzz et recommandations sur Internet: quels effets sur le box-office?

Dans le secteur cinématographique, les spectateurs potentiels ont aujourd'hui la possibilité de se renseigner sur Internet pour connaître les recommandations des critiques et celles des internautes. Or, plus cette recommandation est portée par un grand nombre d'individus, plus elle fait du bruit: du « buzz ». Cette recherche explore dans quelle mesure ces buzz en ligne peuvent être prédicteurs et/ou influenceurs du box-office, en particulier après la semaine de lancement. Une expérimentation de terrain menée sur 534 films montre que les buzz et plus précisément les recommandations affichées sur le site allocine.com sont significativement corrélées au box-office après la première semaine. Différents développements montrent que ces recommandations peuvent non seulement prédire, mais aussi influencer le box-office.

A web usage lattice based mining approach for intelligent web personalization

With the explosive growth of information available on the World Wide Web, it has become much more difficult to access relevant information from the Web. One possible approach to solve this problem is web personalization. In this paper, we propose a novel WUL (Web Usage Lattice) based mining approach for mining association access pattern rules for personalized web recommendations. The proposed approach aims to mine a reduced set of effective association pattern rules for enhancing the online performance of web recommendations. We have incorporated the proposed approach into a personalized web recommender system known as AWARS. The performance of the proposed approach is evaluated based on the efficiency and the quality. In the efficiency evaluation, we measure the number of generated rules and the runtime for online recommendations. In the quality evaluation, we measure the quality of the recommendation service based on precision, satisfactory and applicability. This paper will discuss the proposed WUL‐based mining approach, and give the performance of the proposed approach in comparison with the Apriori‐based algorithms.

Advice through mice: individual and advisor-system differences in online recommendations

Internet advice and recommendations technologies provide innumerable ways for companies to help consumers make choices. However, basic questions about the acceptance and usefulness of online advice remain unanswered. A large web-based survey found differences in use of advice sources and topics, trust and confidence in human versus automated advice and preferences for advice speed and ease of use. Tactics and strategies for web vendor implementation of online advice systems are discussed.

QSIA – a Web-based environment for learning, assessing and knowledge sharing in communities

This paper describes a Web-based and distributed system named QSIA that serves as an environment for learning, assessing and knowledge sharing. QSIA – Questions Sharing and Interactive Assignments – offers a unified infrastructure for developing, collecting, managing and sharing of knowledge items. QSIA enhances collaboration in authoring via online recommendations and generates communities of teachers and learners. At the same time, QSIA fosters individual learning and might promote high-order thinking skills among its users. QSIA's community, conceptual architecture, structure overview and implementations are discussed.

Research Using the Internet to Complete Ergonomics Assessments of Offices

A method was developed for completing office ergonomic assessments using the Internet specifically designed for non-complex situations, and particularly as a proactive measure. However, it is as effective reactively, if the musculoskeletal disorder symptoms are not too complex. The system was tested in a major energy services firm as well as across a group of people interested in musculoskeletal disorders (MSDs) in the office. The online recommendations are similar to those developed by an onsite assessment. People were satisfied with the results. The benefits of the approach were seen in time to complete the assessment being cut by 57% and the total cost reduced by 73%. In nearly 20% of the online assessments, an onsite assessment was recommended due to complex or severe MSD symptoms. Even accounting for the additional cost of the onsite assessments, this method resulted in a cost reduction of approximately 50% and 37% reduction in time to complete the assessments.

Beijing: a conference of commitments?

The author of this article holds the view that the Declaration and Platform for Action at the UN Fourth World Conference on Women held in Beijing in 1995 was the product of the most highly participatory process ever organized under the auspices of the UN. The Declaration and Platform expressed the strongest views on gender equality, empowerment, and justice that governments have ever endorsed. These documents were the consolidation of gains made by women in previous UN conferences. The 135-page Platform can be used at all levels of decision making. Governments and international can be held accountable for its provisions. The Platform exposes the problems violence and exploitation against women and girls as well as the revelation that environmental destruction is due to an unsustainable pattern of consumption and production, particularly in developed countries. Conference participants included about 3000 nongovernmental groups (NGOs). The Women's Linkage Caucus and WEDO served to facilitate the advocacy process by providing briefings on text still under negotiation and providing on-line recommendations from the 1995 and 1994 Commission on the Status of Women preparatory committee meetings. A scoreboard that tracked government's commitment at the 1995 preparatory committee meetings was reinstated in Beijing. The information was conveyed on the Internet. The European Union is credited with diluting the language about government commitment to the Platform. Governments are still given responsibility for implementation, and the need for political will is stressed (paragraph 293). Paragraph 297 indicates the process for implementation of the Platform and coordination with NGOs. Although the Platform recognizes the importance of women's groups and other NGOs, the responsibility for implementation is still given to governments.