Search results

This paper aims to propose a novel approach which integrates collocations and domain concepts for Chinese cosmetic word of mouth (WOM) sentiment classification. Most sentiment analysis works by collecting sentiment scores from each unigram or bigram. However, not every unigram or bigram in a WOM document contains sentiments. Chinese collocations consist of the main sentiments of WOM. This paper reduces the complexity of the document dimensionality and makes an improvement for sentiment classification.

This paper builds two contextual lexicons for feature words and sentiment words, respectively. Based on these contextual lexicons, this paper uses the techniques of associated rules and mutual information to build possible Chinese collocation sets. This paper applies preference vector modelling as the vector representation approach to catch the relationship between Chinese collocations and their associated concepts.

This paper compares the proposed preference vector models with benchmarks, using three classification techniques (i.e. support vector machine, J48 decision tree and multilayer perceptron). According to the experimental results, the proposed models outperform all benchmarks evaluated by the criterion of accuracy.

This paper focuses on Chinese collocations and proposes a novel research approach for sentiment classification. The Chinese collocations used in this paper are adaptable to the content and domains. Finally, this paper integrates collocations with the preference vector modelling approach, which not only achieves a better sentiment classification performance for Chinese WOM documents but also avoids the curse of dimensionality.

The author presents new estimates of the probability weighting functions found in rank-dependent theories of choice under risk. These estimates are unusual in two senses. First, they are free of functional form assumptions about both utility and weighting functions, and they are entirely based on binary discrete choices and not on matching or valuation tasks, though they depend on assumptions concerning the nature of probabilistic choice under risk. Second, estimated weighting functions contradict widely held priors of an inverse-s shape with fixed point well in the interior of the (0,1) interval: Instead the author usually finds populations dominated by “optimists” who uniformly overweight best outcomes in risky options. The choice pairs used here mostly do not provoke similarity-based simplifications. In a third experiment, the author shows that the presence of choice pairs that provoke similarity-based computational shortcuts does indeed flatten estimated probability weighting functions.

The purpose of this paper is to propose an approach to incorporate contextual information into collaborative filtering (CF) based on the restricted Boltzmann machine (RBM) and deep belief networks (DBNs). Traditionally, neither the RBM nor its derivative model has been applied to modeling contextual information. In this work, the authors analyze the RBM and explore how to utilize a user’s occupation information to enhance recommendation accuracy.

The proposed approach is based on the RBM. The authors employ user occupation information as a context to design a context-aware RBM and stack the context-aware RBM to construct DBNs for recommendations.

The experiments on the MovieLens data sets show that the user occupation-aware RBM outperforms other CF models, and combinations of different context-aware models by mutual information can obtain better accuracy. Moreover, the context-aware DBNs model is superior to baseline methods, indicating that deep networks have more qualifications for extracting preference features.

To improve recommendation accuracy through modeling contextual information, the authors propose context-aware CF approaches based on the RBM. Additionally, the authors attempt to introduce hybrid weights based on information entropy to combine context-aware models. Furthermore, the authors stack the RBM to construct a context-aware multilayer network model. The results of the experiments not only convey that the context-aware RBM has potential in terms of contextual information but also demonstrate that the combination method, the hybrid recommendation and the multilayer neural network extension have significant benefits for the recommendation quality.

Shows that traditional product mapping methods for product positioning analysis fail in international settings due to the high variability of product preferences within each country and the lack of a common product perception among countries. Shows how explicitly incorporating variation in the product positioning analysis can overcome both of these problems. Uses a comparison of how Japanese and US consumers differ in their perceptions of the gift market for young males to illustrate how the proposed method differs from traditional methods. Indicates that Japanese consumers perceive the gift market much more uniformly than Americans.

The purpose of this paper is to discuss the concept of sustainability as a new paradigm regarding food consumption and, by means of a case study from the aquaculture sector, to illustrate how sustainability elements may lead to a new paradigm in food consumption.

The study described involved sensory analyses and personal responses from different consumers representing the population for who the product is intended. Standard methods were adopted for field and laboratory studies.

The experimental studies have shown that appearance, flavour, odour, texture and overall acceptance of farmed salmon is at least as accepted as wild salmon. The sustainability analysis has shown that under the right conditions, sustainability elements may be applied in aquaculture as a means to improve quality and catalyse sustainable food consumption.

The work was carried out in order to discuss the extent to which the concept of sustainability may apply to food consumption projects.

This is the first time a holistic analysis of the links between sustainability in food consumption projects has been made. The paper provides useful data and knowledge on which further research can be carried out.

Traditionally, the distribution activities of a firm have been regarded solely as a cost of doing business. Because of this orientation, the analytical techniques applied to the solutions of problems in this area have tended to be optimising models aimed at reducing total cost subject to various constraints. Typically, service levels were incorporated either as an absolute level requirement so that the specific demand restricted the optimising technique or as an opportunity cost of lost sales with this cost included as a part of the total objective function to be minimised.

In our previous articles we have described how turning points can be identified and how qualitative techniques can be applied when either sudden system changes have occurred or there are relatively few available data and various judgmental/expert opinion techniques must be utilized. Time‐series analysis techniques help identify systematic variation in historical data and provide the basis for future statistical projections. As knowledge of market, economics, and other dynamics is obtained from market research, statistical analysis, and experiments, such information should be incorporated into causal forecasting models. In this article, we will consider some of the more commonly used causal models and their forecasting accuracy, with major emphasis on econometric, marketing, and simulation models.

Reviews the literature on consumer‐perceived risk over the past 30 years. The review begins by establishing perceived risk’s relationship with related marketing constructs such as involvement and trust. It then tackles some debates within the literature, concerning subjective and objective risk and differences between the concepts of risk and uncertainty. It describes how different models have been devised and operationalised to measure risk and how these have developed over the years. Aims to identify and report the theoretical and model developments over the past 30 years and to propose criteria which researchers can use in deciding the most useful model for their own research. The criteria are: understanding, prediction, suitability for reliability and validity assessment, practicality and usability. It is suggested that the basic two‐component model is still the most generally useful for researchers and practitioners alike.

The purpose of the experiment reported here was to examine Internet user concerns and perceptions of online shopping. The attitude of Internet users toward online shopping was measured using the Fishbein model. The relative factors influencing user attitudes toward online shopping and the relationship between the attitude and the influence factors were explored. The results show that the Fishbein model can effectively measure consumer attitudes and the examined consumer characteristics were important influence factors on consumer attitudes and online shopping decisions.