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。

Users often struggle to select choosing among similar online services. To help them make informed decisions, it is important to establish a service reputation measurement mechanism. User-provided feedback ratings serve as a primary source of information for this mechanism, and ensuring the credibility of user feedback is crucial for a reliable reputation measurement. Most of the previous studies use passive detection to identify false feedback without creating incentives for honest reporting. Therefore, this study aims to develop a reputation measure for online services that can provide incentives for users to report honestly.

In this paper, the authors present a method that uses a peer prediction mechanism to evaluate user credibility, which evaluates users’ credibility with their reports by applying the strictly proper scoring rule. Considering the heterogeneity among users, the authors measure user similarity, identify similar users as peers to assess credibility and calculate service reputation using an improved expectation-maximization algorithm based on user credibility.

Theoretical analysis and experimental results verify that the proposed method motivates truthful reporting, effectively identifies malicious users and achieves high service rating accuracy.

The proposed method has significant practical value in evaluating the authenticity of user feedback and promoting honest reporting.

The paper aims to investigate differences in non-professional and professional stock investors’ trust in and tendency to follow financial analysts’ buy and sell recommendations.

Online experiment conducted in Sweden in March 2022 comparing non-professional private investors (n = 80), professional investors (n = 33), and master students in finance (n = 28). Information was presented about four company stocks listed on the New York stock exchange. Two stocks were buy-recommended and two stocks sell-recommended by financial analysts. For one stock of each type, the recommendation was presented to participants. Dependent variables were predictions of the stock price after three months, ratings of confidence in the predictions and choices of holding, buying or selling the stock. Ratings were also made of the importance of presented stock-related information as well as trust in analysts’ skill and integrity.

More positive return predictions were made of buy-recommended than sell-recommended stocks. Non-professionals and to some degree finance students tended to trust financial analysts more than professional investors did and they were more influenced by the presentation of the buy recommendations. All groups made too optimistic return predictions, but the professionals were less confident in their predictions, more likely to sell the stocks and lost less on their investments.

A new finding is that non-professional stock investors are more likely than professional stock investors to trust financial analysts and follow their recommendations. It suggests that financial analysts’ recommendations influence non-professional investors to take unmotivated investment risks. Non-professionals in the stock market should hence be advised to exercise more caution in following analysts’ recommendations.

Given the critical role of user-generated content (UGC) in e-commerce, exploring various aspects of UGC can aid in understanding user purchase intention and commodity recommendation. Therefore, this study investigates the impact of UGC on purchase decisions and proposes new recommendation models based on sentiment analysis, which are verified in Douban, one of the most popular UGC websites in China.

After verifying the relationship between various factors and product sales, this study proposes two models, collaborative filtering recommendation model based on sentiment (SCF) and hidden factors topics recommendation model based on sentiment (SHFT), by combining traditional collaborative filtering model (CF) and hidden factors topics model (HFT) with sentiment analysis.

The results indicate that sentiment significantly influences purchase intention. Furthermore, the proposed sentiment-based recommendation models outperform traditional CF and HFT in terms of mean absolute error (MAE) and root mean square error (RMSE). Moreover, the two models yield different outcomes for various product categories, providing actionable insights for organizers to implement more precise recommendation strategies.

The findings of this study advocate the incorporation of UGC sentimental factors into websites to heighten recommendation accuracy. Additionally, different recommendation strategies can be employed for different products types.

This study introduces a novel perspective to the recommendation algorithm field. It not only validates the impact of UGC sentiment on purchase intention but also evaluates the proposed models with real-world data. The study provides valuable insights for managerial decision-making aimed at enhancing recommendation systems.

This study aims to provide a precise understanding of how corporate sustainability information is used in socially responsible investing (SRI). The study is motivated by the lack of a recognised body of knowledge on this issue. This study, therefore, collates and reviews relevant studies (67 studies) to provide guidance to investors interested in SRI and identify a research agenda for academics desiring to contribute to this area.

This study conducts a systemic literature review employing recognised key words and searching the Web of Science. HistCite is utilised to ensure important cited studies are not missed from the collection. The review was conducted from two perspectives: (1) sources of sustainability information and (2) how the information is used in SRI.

The review identifies five major sources of sustainability information, including corporate reports, ESG ratings, industry affiliation, news and private communication with firms. These sources of information play different roles in the cross section of SRI strategies (i.e. negative and positive screening, active ownership and integration). This study provides guidance on how to use this information in SRI and provides recommendations for future research on how analysts interact with the information, how different informational characteristics impact implementation, ways to improve data quality, improvements to analysis methods and where data use needs to be extended into new strategies.

This review contributes to the SRI literature by inventorying studies of an important, yet omitted aspect, namely, sustainability information. This work also enriches the literature on corporate sustainability information by investigating how this information can be used for a specific purpose, namely, SRI. Given the increasing interest in SRI, this review will provide much-needed guidance for a range of practitioners, including investors and regulators.

Multiple topics often exist on social media platforms that compete for users' attention. To explore how users’ attention transfers in the context of multitopic competition can help us understand the development pattern of the public attention.

This study proposes the prediction model for the attention transfer behavior of social media users in the context of multitopic competition and reveals the important influencing factors of users' attention transfer. Microblogging features are selected from the dimensions of users, time, topics and competitiveness. The microblogging posts on eight topic categories from Sina Weibo, the most popular microblogging platform in China, are used for empirical analysis. A novel indicator named transfer tendency of a feature value is proposed to identify the important factors for attention transfer.

The accuracy of the prediction model based on Light GBM reaches 91%. It is found that user features are the most important for the attention transfer of microblogging users among all the features. The conditions of attention transfer in all aspects are also revealed.

The findings can help governments and enterprises understand the competition mechanism among multiple topics and improve their ability to cope with public opinions in the complex environment.

With the rapid advancement in the automotive industry, the friction coefficient (FC), wear rate (WR) and weight loss (WL) have emerged as crucial parameters to measure the performance of automotive braking systems, so the FC, WR and WL of friction material are predicted and analyzed in this work, with an aim of achieving accurate prediction of friction material properties.

Genetic algorithm support vector machine (GA-SVM) model is obtained by applying GA to optimize the SVM in this work, thus establishing a prediction model for friction material properties and achieving the predictive and comparative analysis of friction material properties. The process parameters are analyzed by using response surface methodology (RSM) and GA-RSM to determine them for optimal friction performance.

The results indicate that the GA-SVM prediction model has the smallest error for FC, WR and WL, showing that it owns excellent prediction accuracy. The predicted values obtained by response surface analysis are closed to those of GA-SVM model, providing further evidence of the validity and the rationality of the established prediction model.

The relevant results can serve as a valuable theoretical foundation for the preparation of friction material in engineering practice.

The crux of this paper is to unveil efficient features and practical tools that can predict credit default.

Annual data of non-financial listed companies were taken from 2000 to 2020, along with 71 financial ratios. The dataset was bifurcated into three panels with three default assumptions. Logistic regression (LR) and k-nearest neighbor (KNN) binary classification algorithms were used to estimate credit default in this research.

The study’s findings revealed that features used in Model 3 (Case 3) were the efficient and best features comparatively. Results also showcased that KNN exposed higher accuracy than LR, which proves the supremacy of KNN on LR.

Using only two classifiers limits this research for a comprehensive comparison of results; this research was based on only financial data, which exhibits a sizeable room for including non-financial parameters in default estimation. Both limitations may be a direction for future research in this domain.

This study introduces efficient features and tools for credit default prediction using financial data, demonstrating KNN’s superior accuracy over LR and suggesting future research directions.

For ranking aggregation in crowdsourcing task, the key issue is how to select the optimal working group with a given number of workers to optimize the performance of their aggregation. Performance prediction for ranking aggregation can solve this issue effectively. However, the performance prediction effect for ranking aggregation varies greatly due to the different influencing factors selected. Although questions on why and how data fusion methods perform well have been thoroughly discussed in the past, there is a lack of insight about how to select influencing factors to predict the performance and how much can be improved of.

In this paper, performance prediction of multivariable linear regression based on the optimal influencing factors for ranking aggregation in crowdsourcing task is studied. An influencing factor optimization selection method based on stepwise regression (IFOS-SR) is proposed to screen the optimal influencing factors. A working group selection model based on the optimal influencing factors is built to select the optimal working group with a given number of workers.

The proposed approach can identify the optimal influencing factors of ranking aggregation, predict the aggregation performance more accurately than the state-of-the-art methods and select the optimal working group with a given number of workers.

To find out under which condition data fusion method may lead to performance improvement for ranking aggregation in crowdsourcing task, the optimal influencing factors are identified by the IFOS-SR method. This paper presents an analysis of the behavior of the linear combination method and the CombSUM method based on the optimal influencing factors, and optimizes the task assignment with a given number of workers by the optimal working group selection method.

This research is aimed at preparing landslide susceptibility using spatial analysis and soft computing machine learning techniques based on convolutional neural networks (CNNs), artificial neural networks (ANNs) and logistic regression (LR) models.

Using the Geographical Information System (GIS), a spatial database including topographic, hydrologic, geological and landuse data is created for the study area. The data are randomly divided between a training set (70%), a validation (10%) and a test set (20%).

The validation findings demonstrate that the CNN model (has an 89% success rate and an 84% prediction rate). The ANN model (with an 84% success rate and an 81% prediction rate) predicts landslides better than the LR model (with a success rate of 82% and a prediction rate of 79%). In comparison, the CNN proves to be more accurate than the logistic regression and is utilized for final susceptibility.

Land cover data and geological data are limited in largescale, making it challenging to develop accurate and comprehensive susceptibility maps.

It helps to identify areas with a higher likelihood of experiencing landslides. This information is crucial for assessing the risk posed to human lives, infrastructure and properties in these areas. It allows authorities and stakeholders to prioritize risk management efforts and allocate resources more effectively.

The social implications of a landslide susceptibility map are profound, as it provides vital information for disaster preparedness, risk mitigation and landuse planning. Communities can utilize these maps to identify vulnerable areas, implement zoning regulations and develop evacuation plans, ultimately safeguarding lives and property. Additionally, access to such information promotes public awareness and education about landslide risks, fostering a proactive approach to disaster management. However, reliance solely on these maps may also create a false sense of security, necessitating continuous updates and integration with other risk assessment measures to ensure effective disaster resilience strategies are in place.

Landslide susceptibility mapping provides a proactive approach to identifying areas at higher risk of landslides before any significant events occur. Researchers continually explore new data sources, modeling techniques and validation approaches, leading to a better understanding of landslide dynamics and susceptibility factors.