Ranking Reputation and Quality in Online Rating Systems

Liao, Hao; Zeng, An; Xiao, Rui; Ren, Zhuo Ming; Chen, Duan Bing; Zhang, Yi Cheng

doi:10.1371/journal.pone.0097146

Cited by 53 publications

(45 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we set = 3 which is suggested by the proposers [17]. At the same time, Liao et al also presented another similar algorithm, called IARR2, by introducing a penalty factor to IARR.…”

Section: Iterative Ranking Frameworkmentioning

confidence: 99%

See 1 more Smart Citation

Eliminating the Effect of Rating Bias on Reputation Systems

Ren

et al. 2018

Complexity

View full text Add to dashboard Cite

The ongoing rapid development of the e-commercial and interest-base websites makes it more pressing to evaluate objects' accurate quality before recommendation. The objects' quality is often calculated based on their historical information, such as selected records or rating scores. Usually high quality products obtain higher average ratings than low quality products regardless of rating biases or errors. However, many empirical cases demonstrate that consumers may be misled by rating scores added by unreliable users or deliberate tampering. In this case, users' reputation, that is, the ability to rate trustily and precisely, makes a big difference during the evaluation process. Thus, one of the main challenges in designing reputation systems is eliminating the effects of users' rating bias. To give an objective evaluation of each user's reputation and uncover an object's intrinsic quality, we propose an iterative balance (IB) method to correct users' rating biases. Experiments on two datasets show that the IB method is a highly self-consistent and robust algorithm and it can accurately quantify movies' actual quality and users' stability of rating. Compared with existing methods, the IB method has higher ability to find the "dark horses," that is, not so popular yet good movies, in the Academy Awards.

show abstract

Section: Iterative Ranking Frameworkmentioning

confidence: 99%

“…In the ideal case, = 1 indicates that the two ranking lists are exactly the same. Figure 3 shows the MSE value for IB method with different ; see (17). We also present other representative algorithms for comparisons.…”

Section: Evaluation Metricsmentioning

confidence: 99%

Eliminating the Effect of Rating Bias on Reputation Systems

Ren

et al. 2018

Complexity

View full text Add to dashboard Cite

show abstract

“…The main task of recommender system is to predict future links of each target user based on historical rating records [31,32,[35][36][37], in which the whole data set is divided into a training set and a test set and only the links in training set is known before recommendation. However, in most of the previous studies, as far as we know, the test data set is sampled randomly without consider the temporal order of the links, leading to a logical disorder in the recommendation process, i.e., predicting the past links in test set on the basis of the future links in training set.…”

Section: Related Workmentioning

confidence: 99%

Information filtering in evolving online networks

Chen

Zhang

et al. 2018

Physics Letters A

View full text Add to dashboard Cite

Recommender systems use the records of users' activities and profiles of both users and products to predict users' preferences in the future. Considerable works towards recommendation algorithms have been published to solve the problems such as accuracy, diversity, congestion, cold-start, novelty, coverage and so on. However, most of these research did not consider the temporal effects of the information included in the users' historical data. For example, the segmentation of the training set and test set was completely random, which was entirely different from the real scenario in recommender systems. More seriously, all the objects are treated as the same, regardless of the new, the popular or obsoleted products, so do the users. These data processing methods always lose useful information and mislead the understanding of the system's state. In this paper, we detailed analyzed the difference of the network structure between the traditional random division method and the temporal division method on two benchmark data sets, Netflix and MovieLens. Then three classical recommendation algorithms, Global Ranking method, Collaborative Filtering and Mass Diffusion method, were employed. The results show that all these algorithms became worse in all four key indicators, ranking score, precision, popularity and diversity, in the temporal scenario. Finally, we design a new recommendation algorithm based on both users' and objects' first appearance time in the system. Experimental results showed that the new algorithm can greatly improve the accuracy and other metrics.

show abstract

“…Zhou et al [6] developed a correlation based ranking algorithm (short for CR), where the user's reputation is determined by the Pearson correlation coefficient between his/her rating vector and the corresponding objects' calculated quality vector. Liao et al [16] designed an iterative algorithm with reputation redistribution (short for IARR), presenting the reputation redistribution process to eliminate noisy information in the iterations. Meanwhile, the IARR method was modified by introducing two penalty factors (small-degree users or objects cannot have very high reputation or quality), namely IARR2 method [16], leading the objects rated by only low reputation users with less quality and the users who only rate a small number of objects with lower reputation.…”

Section: Introductionmentioning

confidence: 99%

“…Liao et al [16] designed an iterative algorithm with reputation redistribution (short for IARR), presenting the reputation redistribution process to eliminate noisy information in the iterations. Meanwhile, the IARR method was modified by introducing two penalty factors (small-degree users or objects cannot have very high reputation or quality), namely IARR2 method [16], leading the objects rated by only low reputation users with less quality and the users who only rate a small number of objects with lower reputation. In empirical rating systems, users with different degrees are evolved by different mechanisms [17][18][19].…”

Section: Introductionmentioning

confidence: 99%