Search results

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.

In this paper, with the goal of reducing the fuel consumption of UAV, the engine performance optimization is studied and on the basis of aircraft/engine integrated control, the minimum fuel consumption optimization method of engine given thrust is proposed. In the case of keeping the given thrust of the engine unchanged, the main fuel flow of the engine without being connected to the afterburner is optimally controlled so as to minimize the fuel consumption.

In this study, the reference model real-time optimization control method is adopted. The engine reference model uses a nonlinear real-time mathematical model of a certain engine component method. The quasi-Newton method is adopted in the optimization algorithm. According to the optimization variable nozzle area, the turbine drop-pressure ratio corresponding to the optimized nozzle area is calculated, which is superimposed with the difference of the drop-pressure ratio of the conventional control plan and output to the conventional nozzle controller of the engine. The nozzle area is controlled by the conventional nozzle controller.

The engine real-time minimum fuel consumption optimization control method studied in this study can significantly reduce the engine fuel consumption rate under a given thrust. At the work point, this is a low-altitude large Mach work point, which is relatively close to the edge of the flight envelope. Before turning on the optimization controller, the fuel consumption is 0.8124 kg/s. After turning on the optimization controller, you can see that the fuel supply has decreased by about 4%. At this time, the speed of the high-pressure rotor is about 94% and the temperature after the turbine can remain stable all the time.

The optimal control method of minimum fuel consumption for the given thrust of UAV is proposed in this paper and the optimal control is carried out for the nozzle area of the engine. At the same time, a method is proposed to indirectly control the nozzle area by changing the turbine pressure ratio. The relevant UAV and its power plant designers and developers may consider the results of this study to reach a feasible solution to reduce the fuel consumption of UAV.

Fuel consumption optimization can save fuel consumption during aircraft cruising, increase the economy of commercial aircraft and improve the combat radius of military aircraft. With the increasingly wide application of UAVs in military and civilian fields, the demand for energy-saving and emission reduction will promote the UAV industry to improve the awareness of environmental protection and reduce the cost of UAV use and operation.

The purpose of this paper is to examine the effects of cross-border mergers and acquisitions (M&As) by firms in the emerging marketing on stock market cumulative abnormal returns (CARs). This research focuses on the acquiring firms in emerging markets and broadens the existing scope which highlights the M&As by firms in developed countries.

Regarding the controversial argument on the effect of cross-border M&As, the authors introduce a resource-based theory to explain the motivation of M&As by Chinese firms, conduct an event study analysis of 472 international acquisitions by Chinese firms from 2010 to 2015 and indicate cross-border M&As as a positive signal in the stock market.

The results reveal that cross-border M&As result in significantly positive CARs in a short term for the acquiring firms listed in mainland markets but not for that in the Hong Kong market. Furthermore, consistent with signaling theory and the investors’ heuristic thinking in decision-making, investors may adopt the technological innovation capability of the country where the target firms locate, and the acquiring firm’s preannouncement in shaping their positive judgment of the acquiring firm’s near future performance.

The authors distinguished the responses of the investors from the mainland and Hong Kong stock markets and investigated how the knowledge of the national innovation capability of the target firm and acquisition preannouncement influence the investors’ interpretation of the cross-border M&As as a market signal.