Search results

Textual information about restaurants, such as online reviews and food categories, is essential for consumer purchase decisions. However, previous restaurant recommendation studies have failed to use textual information containing essential information for predicting consumer preferences effectively. This study aims to propose a novel restaurant recommendation model to effectively estimate the assessment behaviors of consumers for multiple restaurant attributes.

The authors collected 1,206,587 reviews from 25,369 consumers of 46,613 restaurants from Yelp.com. Using these data, the authors generated a consumer preference vector by combining consumer identity and online consumer reviews. Thereafter, the authors combined the restaurant identity and food categories to generate a restaurant information vector. Finally, the nonlinear interaction between the consumer preference and restaurant information vectors was learned by considering the restaurant attribute vector.

This study found that the proposed recommendation model exhibited excellent performance compared with state-of-the-art models, suggesting that combining various textual information on consumers and restaurants is a fundamental factor in determining consumer preference predictions.

To the best of the authors’ knowledge, this is the first study to develop a personalized restaurant recommendation model using textual information from real-world online restaurant platforms. This study also presents deep learning mechanisms that outperform the recommendation performance of state-of-the-art models. The results of this study can reduce the cost of exploring consumers and support effective purchasing decisions.

关于餐厅的文本信息, 如在线评论和食品分类, 对于消费者的购买决策产生至关重要。然而, 先前的餐厅推荐研究未能有效利这些文本信息去预测消费者喜好。本研究提出了一种新颖的餐厅推荐模型, 以有效估计消费者对多个餐厅属性的评估行为。

我们从 Yelp.com 收集了来自25,369名消费者对 46,613 家餐厅的 1,206,587 条评论。利用这些数据, 我们通过结合消费者身份和在线消费者评论生成了消费者偏好向量。然后, 我们结合了餐厅身份和食品分类来生成餐厅信息向量。最后, 考虑到餐厅属性向量, 本研究调查了消费者偏好和餐厅信息向量之间的非线性交互关系。

我们发现, 所提出的推荐模型相比于之前最先进的模型表现出更优秀的性能, 这表明结合消费者和餐厅的各种文本信息是预测消费者喜好的基本因素。

据我们所知, 这是第一项利用来自真实在线餐厅平台的文本信息开发个性化餐厅推荐模型的研究。本研究还提出了胜过最先进模型的深度学习机制。本研究的结果可以降低探索消费者行为的成本并支持有效的购买决策。

Most previous studies predicting review helpfulness ignored the significance of deep features embedded in review text and instead relied on hand-crafted features. Hand-crafted and deep features have the advantages of high interpretability and predictive accuracy. This study aims to propose a novel review helpfulness prediction model that uses deep learning (DL) techniques to consider the complementarity between hand-crafted and deep features.

First, an advanced convolutional neural network was applied to extract deep features from unstructured review text. Second, this study used previous studies to extract hand-crafted features that impact the helpfulness of reviews and enhance their interpretability. Third, this study incorporated deep and hand-crafted features into a review helpfulness prediction model and evaluated its performance using the Yelp.com data set. To measure the performance of the proposed model, this study used 2,417,796 restaurant reviews.

Extensive experiments confirmed that the proposed methodology performs better than traditional machine learning methods. Moreover, this study confirms through an empirical analysis that combining hand-crafted and deep features demonstrates better prediction performance.

To the best of the authors’ knowledge, this is one of the first studies to apply DL techniques and use structured and unstructured data to predict review helpfulness in the restaurant context. In addition, an advanced feature-fusion method was adopted to better use the extracted feature information and identify the complementarity between features.

大多数先前预测评论有用性的研究忽视了嵌入在评论文本中的深层特征的重要性, 而主要依赖手工制作的特征。手工制作和深层特征具有高解释性和预测准确性的优势。本研究提出了一种新颖的评论有用性预测模型, 利用深度学习技术来考虑手工制作特征和深层特征之间的互补性。

首先, 采用先进的卷积神经网络从非结构化的评论文本中提取深层特征。其次, 本研究利用先前研究中提取的手工制作特征, 这些特征影响了评论的有用性并增强了其解释性。第三, 本研究将深层特征和手工制作特征结合到一个评论有用性预测模型中, 并使用Yelp.com数据集对其性能进行评估。为了衡量所提出模型的性能, 本研究使用了2,417,796条餐厅评论。

广泛的实验验证了所提出的方法优于传统的机器学习方法。此外, 通过实证分析, 本研究证实了结合手工制作和深层特征可以展现出更好的预测性能。

据我们所知, 这是首个在餐厅评论预测中应用深度学习技术, 并结合了结构化和非结构化数据来预测评论有用性的研究之一。此外, 本研究采用了先进的特征融合方法, 更好地利用了提取的特征信息, 并识别了特征之间的互补性。

The existing collaborative filtering algorithm may select an insufficiently representative customer as the neighbor of a target customer, which means that the performance in providing recommendations is not sufficiently accurate. This study aims to investigate the impact on recommendation performance of selecting influential and representative customers.

Some studies have shown that review helpfulness and consistency significantly affect purchase decision-making. Thus, this study focuses on customers who have written helpful and consistent reviews to select influential and representative neighbors. To achieve the purpose of this study, the authors apply a text-mining approach to analyze review helpfulness and consistency. In addition, they evaluate the performance of the proposed methodology using several real-world Amazon review data sets for experimental utility and reliability.

This study is the first to propose a methodology to investigate the effect of review consistency and helpfulness on recommendation performance. The experimental results confirmed that the recommendation performance was excellent when a neighbor was selected who wrote consistent or helpful reviews more than when neighbors were selected for all customers.

This study investigates the effect of review consistency and helpfulness on recommendation performance. Online review can enhance recommendation performance because it reflects the purchasing behavior of customers who consider reviews when purchasing items. The experimental results indicate that review helpfulness and consistency can enhance the performance of personalized recommendation services, increase customer satisfaction and increase confidence in a company.

The current study investigates the impact on perceived review helpfulness of the simultaneous processing of information from multiple cues with various central and peripheral cue combinations based on the elaboration likelihood model (ELM). Thus, the current study develops and tests hypotheses by analyzing real-world review data with a text mining approach in e-commerce to investigate how information consistency (rating inconsistency, review consistency and text similarity) influences perceived helpfulness. Moreover, the role of product type is examined in online consumer reviews of perceived helpfulness.

The current study collected 61,900 online reviews, including 600 products in six categories, from Amazon.com. Additionally, 51,927 reviews were filtered that received helpfulness votes, and then text mining and negative binomial regression were applied.

The current study found that rating inconsistency and text similarity negatively affect perceived helpfulness and that review consistency positively affects perceived helpfulness. Moreover, peripheral cues (rating inconsistency) positively affect perceived helpfulness in reviews of experience goods rather than search goods. However, there is a lack of evidence to demonstrate the hypothesis that product types moderate the effectiveness of central cues (review consistency and text similarity) on perceived helpfulness.

Previous studies have mainly focused on numerical and textual factors to investigate the effect on perceived helpfulness. Additionally, previous studies have independently confirmed the factors that affect perceived helpfulness. The current study investigated how information consistency affects perceived helpfulness and found that various combinations of cues significantly affect perceived helpfulness. This result contributes to the review helpfulness and ELM literature by identifying the impact on perceived helpfulness from a comprehensive perspective of consumer review and information consistency.

The purpose of this study is to investigate the intergranular corrosion (IGC) susceptibility of a nitrogen-containing austenitic stainless steel QN2109. The intergranular corrosion (IGC) susceptibility of a nitrogen-containing austenitic stainless steel QN2109 was investigated.

The double-loop electrochemical potentiodynamic reactivation (DL-EPR) tests were carried out. Scanning electron microscopy and atomic force microscopy were used to characterize the microstructure.

The optimized test condition for QN2109 was 1 M H₂SO₄ + 0.01 M NH₄SCN at 40°C. The nose temperature of the temperature–time–sensitization (TTS) curve of QN2109 plot was approximately 750°C. Moreover, the IGC susceptibility started to appear at approximately 120 min. The Cr-depletion zone of QN2109 was generated by the formation of M23C6 rather than by the addition of nitrogen. The depth–width ratio of the grain boundaries after the DL-EPR tests decreased as the aging temperature increased. The degree of Cr depletion and size of the Cr-depletion zone at the grain boundary were reflected by the degree of sensitization and depth–width ratio, respectively.

The optimized test condition for DL-EPR tests of a nitrogen-containing austenitic stainless steel QN2109 was investigated. The TTS curve of QN2109 was first plotted to avoid IGC failure. The morphology of the Cr-depletion zone was reflected by the depth–width ratio.

In this chapter, we investigate whether the option contract can coordinate a supply chain when supply chain members have fairness concerns. Specifically, we consider a supply chain consisting of a manufacturer and a retailer where the two members can be either rational or fair-minded, and explore the condition under which the supply chain can be coordinated using an option contract. We follow the traditional newsvendor model by assuming that the market demand is stochastic with a cumulative distribution function and the retail price is exogenous. Under the option contract, the manufacturer’s decision variables include its option price and its exercise price, and the retailer is to decide its order quantity. We derive the equilibrium results for four different scenarios, that is, (i) both the two members are rational, (ii) the supplier is rational but the retailer is fair-minded, (iii) the supplier is fair-minded but the retailer is rational, and (iv) both are fair-minded. While the option contract can coordinate the supply chain when either of the two members is rational, we also find that when both the two members are rational, the option contract can coordinate the supply chain only under some specific conditions. Furthermore, we investigate whether the two members will suffer the disadvantageous or the advantageous inequality in the equilibrium and find some interesting findings.

In recent years, many new and interesting business models for Internet-based selling have emerged with the advent of electronic commerce, one of which is the Internet-based group-buying. Since group-buying can be quickly built and removed, and the consumers can pay a lower price for the product through it, the group-buying can be a new online promotion form. In this chapter we build up a two-period pricing model for a supply chain when a supply chain member utilizes group-buying program to promote its products. In detail, we consider a supply chain consisting of a supplier and a retailer, where the supplier or retailer may launch a group-buying program to promote the products via a group-buying web site in the promotion period (i.e., the first period), as well as the supplier may sell its products through the retailer traditionally in both periods. Utilizing game theory, we derive the equilibrium decisions of the two supply chain members in three different scenarios, that is, (i) there is no group-buying program, (ii) the supplier launches a group-buying program, and (iii) the retailer launches a group-buying program. Analysis of the equilibrium decisions illustrates the following results: (i) both, the supplier and the retailer, will set low prices in the promotion period and high prices in the regular period; (ii) this trend will be enhanced when a group-buying program occurs, especially when such program is launched by the supplier; (iii) while the retailer can always benefit from a group-buying program, the supplier’s profit may be reduced under certain conditions; and (iv) in spite of the fact that the supplier’s profit may be damaged by the group-buying program, when the two supply chain members decide to launch a group-buying program, the unique equilibrium is that the supplier will launch such a program.

Grinding may generate high temperature along the arc of grinding zone, especially during the grinding process of difficult‐to‐machine materials. It can cause thermal damage to the ground surface and poor surface integrity. Conventional cooling methods based on large amounts of water‐oil emulsions can be both ineffective and environmentally unacceptable. The purpose of this paper is to offer a new high efficiency cooling method – cryogenic pneumatic mist jet cooling (CPMJ) to enhance heat transfer in the grinding zone during grinding of difficult‐to‐machine materials.

CPMJ equipment is a set up, which can produce water mist of −5°C with jet velocity above 150 m/s and mean particle size below 20 μm at the impingement distance of 10‐40 mm on the symmetry axis. To validate the cooling efficiency of CPMJ equipment, heat transfer experiments were carrying out on it. Finally, CPMJ was applied to the grinding of titanium alloy to verify its cooling effects.

With high penetrative power and water mist of −5°C, CPMJ can greatly improve heat transfer efficiency in the grinding zone. Experimental results, including heat transfer experiments and grinding experiments, indicate that CPMJ has strong cooling ability and can offer better cooling effects compared with cold air jet and traditional flood cooling method. With CPMJ cooling method, grinding zone temperature can be effectively reduced and good surface quality can be achieved during grinding of titanium alloy.

CPMJ cooling method is an effective and pollution‐free way to solve the thermal problems during grinding of difficult‐to‐machine materials.

In today's world, all firms’ corporate social responsibility (CSR) actions are coming under increasing public scrutiny. This is especially true for large companies whose decisions can and do have impact on society. Public service advertisements (PSAs), a mass-media approach, are advertisements which inform audiences of a firm's CSR actions and enhance its public image. In this chapter, we focus on a supply chain system consisting of two firms and their coordination strategy for public service advertising. To describe the synergistic effect between a PSA and a normal commercial advertisement, a modified Nerlove–Arrow model is employed in this chapter. Using differential game theory, we calculate and compare the optimal advertising levels for each stage of the supply chain system under two different decision scenarios, i.e., (i) the two firms make decisions independently and (ii) the two firms make decisions as an integral system. A coordination mechanism on the public service advertising between the two firms has also been proposed for the supply chain system and has been proved effective.

Selective crowdsourcing is an important type of crowdsourcing which has been popularly used in practice. However, because selective crowdsourcing uses a winner-takes-all mechanism, implying that the efforts of most participants except the final winner will be just in vain. The purpose of this paper is to explore why this costly mechanism can become a popularity during the past decade and which type of tasks can fit this mechanism well.

The authors propose a game model between a sponsor and N participants. The sponsor is to determine its reward and the participants are to optimize their effort-spending strategy. In this model, each participant's ability is the private information, and thus, all roles in the system face incomplete information.

The results of this paper demonstrate the following: whether the sponsor can obtain a positive expected payoff are determined by the type of tasks, while the complex tasks with a strong learning effect is more suitable to selective crowdsourcing, as for the other two types of task, the sponsor cannot obtain a positive payoff, or can just gain a rather low payoff; besides the task type, the sponsor's efficiency in using the solutions and the public's marginal cost also influence the result that whether the sponsor can obtain a positive surplus from the winner-takes-all mechanism.

The model presented in this paper is innovative by containing the following characteristics. First, each participant's ability is private information, and thus, all roles in the system face incomplete information. Second, the winner-takes-all mechanism is used, implying that the sponsor's reward will be entirely given to the participant with the highest quality solution. Third, the sponsor's utility from the solutions, as well as the public's cost to complete the task, are both assumed as functions just satisfying general properties.