Enhanced review-based rating prediction by exploiting aside information and user influence

2021 ◽  
pp. 107015
Author(s):  
Shiwen Wu ◽  
Yuanxing Zhang ◽  
Wentao Zhang ◽  
Kaigui Bian ◽  
Bin Cui
2014 ◽  
Vol 11 (3) ◽  
pp. 1-15
Author(s):  
Ike Arisanti ◽  
Isti Fadah ◽  
Novi Puspitasari

This study purposes to analyze the influence of financial and non financial factors to prediction of the rating islamic bond in indonesia. The study used independent variable,that is financial factor (growth, size, profit sharing/fee, liquidity) and non financial factor ( secure and maturity) and dependent variable that is the rating of islamic bond. This study applied logistic regresion analysis with sample collection methods using purposive sampling. After selecting fixed criterias, there were 25 islamic bonds chosen with the numbers of 75 investigation from periods of 2010-2012. The result of this study showed that significantly effect the variable growth (X1) , size(X2), profit sharing/ fee (X3), liquidity (X4), secure (X5), maturity (X6) simultaneously to the rating prediction of islamic bond in indonesia. Partially, variable variables of growth (X1) , size (X2), profit sharing/ fee (X3) which referred not significant affecting to the rating prediction of islamic bond in indonesia. Meanwhile, variables of liquidity (X4), secure (X5), maturity ( X6) referred significant affecting to the rating prediction of islamic bond in indonesia.


IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 101197-101206
Author(s):  
Diao Zhou ◽  
Shengnan Hao ◽  
Haiyang Zhang ◽  
Chenxu Dai ◽  
Yongli An ◽  
...  

2021 ◽  
pp. 1-1
Author(s):  
Juan Guo ◽  
Yu Cheng ◽  
Dehan Luo ◽  
Kin-Yeung Wong ◽  
Kevin Hung ◽  
...  

2021 ◽  
Vol 11 (6) ◽  
pp. 2530
Author(s):  
Minsoo Lee ◽  
Soyeon Oh

Over the past few years, the number of users of social network services has been exponentially increasing and it is now a natural source of data that can be used by recommendation systems to provide important services to humans by analyzing applicable data and providing personalized information to users. In this paper, we propose an information recommendation technique that enables smart recommendations based on two specific types of analysis on user behaviors, such as the user influence and user activity. The components to measure the user influence and user activity are identified. The accuracy of the information recommendation is verified using Yelp data and shows significantly promising results that could create smarter information recommendation systems.


Author(s):  
Xiang LIU ◽  
Yan JIA ◽  
Rong JIANG ◽  
Yong QUAN

Sign in / Sign up

Export Citation Format

Share Document