Learning to evaluate and recommend query in restaurant search systems

Chen, Xian; Lee, Hyang-Won

doi:10.1007/s10257-016-0309-8

Cited by 3 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cost-sensitive learning assigns different weights to each interest point in the sorted list, and the weight α i is learned for each interest point in the list when calculating the sorted list, and the sum of weights α i is 1 and decreases from front to back as the position of interest points in the sorted list changes. The calculated social relationship impact is combined with the cost-sensitive approach to derive the formula for the scoring function as in Equation (12).…”

Section: Cost-sensitive Scoring Functionmentioning

confidence: 99%

“…Step 4 The social relationship influence obtained in step 2 is fused with the recommendation list length and weights obtained in step 3 to generate the recommendation list score is Equation (12).…”

Section: Improved Listmle Recommendation Algorithmmentioning

confidence: 99%

“…Li [11] used the list-level method ListNet to process feature matrices and compare the differences in sorting performance. Chen [12] applied list-level sorting to restaurant recommendation and used the sorting model to learn the results generated by the base model to provide a query and recommendation scheme for vertical search. The above algorithms incorporate different contextual information, and most of them use matrix decomposition to calculate user potential feature vectors, which has some limitations: they only consider the relationship between a single item or two items, and fail to consider the characteristics of the recommendation list as a whole.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

ListMLE-based personalized teaching resources recommendation for online-to-offline hybrid course under smart education environment

wang

Shan

Zou

2022

International Symposium on Artificial Intelligence and Robotics 2022

View full text Add to dashboard Cite

Smart education is a product of the information-based education development, which enhances the intelligence of traditional education and realizes innovative education. According to the personalized learning characteristics of students, with a student-centered approach and relying on Online-to-offline hybrid courses, we have designed a new architecture for recommending educational resources to improve learning effectiveness and promote effective teaching by tapping into students' potential. The use of sequential learning technology for teaching resource recommendation is a popular research direction in intelligent education, and its core is the recommendation algorithm of personalized resources. In order to solve the problem of insufficient location information and low accuracy in the result table based on sorting learning, a recommendation algorithm of interest points based on ListMLE is proposed. Firstly, the ListMLE algorithm is applied to interest point recommendation based on the attention difference of interest point location in the recommendation list. Secondly, the influence of users' social relations is incorporated into the scoring function of ListMLE. Finally, a cost-sensitive method is introduced in the recommendation list calculation process. This paper proposes an online education resource recommendation method for personalized learning. Experimental results show that the algorithm outperforms the baseline ranking learning algorithm in terms of accuracy and recall. The method can be used to study students' learning behaviors and provide a theoretical basis for designing personalized learning programs based on students' learning status.

show abstract

Section: Cost-sensitive Scoring Functionmentioning

confidence: 99%

Section: Improved Listmle Recommendation Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation