Temporal Model of the Online Customer Review Helpfulness Prediction with Regression Methods

Wu, Shih-Hung; Hsieh, Yi-Hsiang; Chen, Liang-Pu; Yang, Ping-Che; Fanghuizhu, Liu

doi:10.1007/978-3-030-02592-2_2

Cited by 7 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was concluded that the numerical review features were more important across all three types of reviews compared with the textual review features [43]. Wu et al [44] highlighted the importance of temporal dimensions and proposed a temporal model for predicting review helpfulness. It was stated that the old reviews would not be that helpful for a product where new reviews come in very often.…”

Section: B Features For Predicting Review Helpfulnessmentioning

confidence: 99%

Profiling Users’ Behavior, and Identifying Important Features of Review “Helpfulness”

et al. 2020

View full text Add to dashboard Cite

The increasing volume of online reviews and the use of review platforms leave tracks that can be used to explore interesting patterns. It is in the primary interest of businesses to retain and improve their reputation. Reviewers, on the other hand, tend to write reviews that can influence and attract people's attention, which often leads to deliberate deviations from past rating behavior. Until now, very limited studies have attempted to explore the impact of user rating behavior on review helpfulness. However, there are more perspectives of user behavior in selecting and rating businesses that still need to be investigated. Moreover, previous studies gave more attention to the review features and reported inconsistent findings on the importance of the features. To fill this gap, we introduce new and modify existing business and reviewer features and propose a user-focused mechanism for review selection. This study aims to investigate and report changes in business reputation, user choice, and rating behavior through descriptive and comparative analysis. Furthermore, the relevance of various features for review helpfulness is identified by correlation, linear regression, and negative binomial regression. The analysis performed on the Yelp dataset shows that the reputation of the businesses has changed slightly over time. Moreover, 46% of the users chose a business with a minimum of 4 stars. The majority of users give 4-star ratings, and 60% of reviewers adopt irregular rating behavior. Our results show a slight improvement by using user rating behavior and choice features. Whereas, the significant increase in R 2 indicates the importance of reviewer popularity and experience features. The overall results show that the most significant features of review helpfulness are average user helpfulness, number of user reviews, average business helpfulness, and review length. The outcomes of this study provide important theoretical and practical implications for researchers, businesses, and reviewers. INDEX TERMS Business reputation, rating behavior, review helpfulness, user profiling, crowd-sourced reviews.

show abstract

Section: B Features For Predicting Review Helpfulnessmentioning

confidence: 99%

Profiling Users’ Behavior, and Identifying Important Features of Review “Helpfulness”

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The previous paper used some metrics to measure how helpful the review is for the customer. A helpfulness rating also called a helpful ratio, is applied if there are two types of feedback captured by the system: helpful and not helpful [8], [25], [26], [35], [36]. In this case, the helpfulness rating is a ratio of the number of helpful votes to the total votes.…”

Section: A Helpfulness Metricsmentioning

confidence: 99%

“…Regression analysis is a representative model for predicting review helpfulness [4], [9], [24], [26], especially in terms of helpfulness rating, which comes from the ratio of the number of helpful votes to the total votes. Tobit modeling, a zerocensored regression, revises the regression model on massive zero-value problems and has become a popular model for predicting the helpfulness rating [7], [8], [25], [27]- [29].…”

Section: B Helpful Vote Prediction Modelsmentioning

confidence: 99%

“…Those objective functions come from the initial assumption that the dependent variable in the model is normally distributed [12]. F1 star rating [1], [4], [7], [8], [25]- [29], F2 review length/words [1], [4], [7], [8], [25]- [29], F3 review length/sentences [26], F4 review text [9], [24], F5 review age/days [1], [29], [30], F6 total votes [4], [8], [25], [29], F7 review order [4], [27], F8 text sentiment [1], [27], [29], F9 sentiment score deviation [4] F10 text complexity [1], F11 readability/The automated readability index [4], [27], [29], F12 review types [1], F13 writing style [27], F14 review uncertainty [29], F15 information-entropy increment [4], F16 emotion (anger, sad, sadness) [25], F17 the average number of words of each sentence [26], F18 ratio of type of words (adverb, noun, preposition) [26] and adjective [30] F19 product type [8], [25], [29], F20 product-description length/words [4], F21 product fea...…”

Section: B Helpful Vote Prediction Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Distribution-Adapted Model for Helpful Vote Prediction

Saptono

Mine

2022

IEEE Access

View full text Add to dashboard Cite

The number of helpful votes on a review is an essential indicator of how much impact the review has on other customers in electronic commerce. Therefore, predicting the number of helpful votes is an important task. Regression analysis and Tobit modeling are typical methods of prediction. Those methods come from the same initial assumption that the number of helpful votes follows a normal distribution on any dataset. However, the assumption is not usually confirmed, and the distribution of the helpful votes often follows other distributions. This paper proposes a framework for investigating the feasibility of building a model that predicts the number of helpful votes according to the distribution of the number of helpful votes. On top of that, considering the review age, we propose an adaptive window size sampling method to evaluate the model on review datasets sorted chronologically. The experimental results validated that the model adapting to the best approximate distribution gives a significant improvement compared to the baseline models. In addition, model evaluation using the adaptive window size sampling method has significant impacts on the performance on large datasets.

show abstract

“…In the case of real reviews, the variable studied number of reviews and information is obtained directly from website with a rank from 0 reviews to 387 reviews. Reviews were gathered in a same period to avoid time biases (Wu et al, 2018).…”

Section: Data Collectionmentioning

confidence: 99%

Drivers of eWOM intensity: differences between hoteliers’ perception and real reviews

Pérez-Aranda¹,

Guerreiro²,

Mendes³

2021

EJTR

View full text Add to dashboard Cite

This study aims to determine whether eWOM intensity is related to use intensity, commitment, and competence of brands’ review sites. The study is applied to hotels on TripAdvisor and compares brand’s perception and real effects. Results of a survey of 332 hotels listed on TripAdvisor are compared with data collected from TripAdvisor. The method consists of comparing these data with the perception of hoteliers, to determine if the drivers use intensity, commitment, and competence have similar effects on eWOM intensity. Regarding correlation analysis, some similarities are found, all drivers included in both models are positively correlated with each explained variable. However, regression analysis revealed differences between drivers of eWOM intensity when the explained variable is based on hoteliers’ perception instead of objective data. While, no variable is significant when eWOM intensity is based on perception, the variable use intensity shows a significant relation, when eWOM intensity is assessed by actual reviews. The findings suggest that use intensity is a determinant factor of eWOM intensity. Furthermore, differences between brands’ perception and real reviews are observed.

show abstract

Temporal Model of the Online Customer Review Helpfulness Prediction with Regression Methods

Cited by 7 publications

References 13 publications

Profiling Users’ Behavior, and Identifying Important Features of Review “Helpfulness”

Profiling Users’ Behavior, and Identifying Important Features of Review “Helpfulness”

Distribution-Adapted Model for Helpful Vote Prediction

Drivers of eWOM intensity: differences between hoteliers’ perception and real reviews

Contact Info

Product

Resources

About