Web Service Usability Analysis Based on User Preferences

This article attempts to closely examine the users' preferences in the author's method of assessing the usability of websites. In particular, the issues bring a closer evaluation of websites by users. It sets rules for the accuracy of users' preferences on the basis of the scoring method. In the considered problem of assessing the usability of websites the methods of decision support, logs, and user preferences on the basis of the scoring method were used. It should be noted that websites and user preferences change over time and usually vary during the design from the pages already available on the network. Website aging forces companies to conduct a new study on the usability of websites. This article presents an original method for usability analysis based on users' preferences. The proposed method compares with other methods of usability of websites and conducts verification of this method on the basis of exemplary websites.

Download Full-text

Improving Ant Collaborative Filtering on Sparsity via Dimension Reduction

Applied Sciences ◽

10.3390/app10207245 ◽

2020 ◽

Vol 10 (20) ◽

pp. 7245

Author(s):

Xiaofeng Liao ◽

Xiangjun Li ◽

Qingyong Xu ◽

Hu Wu ◽

Yongji Wang

Keyword(s):

Collaborative Filtering ◽

Recommender Systems ◽

User Preferences ◽

Ant Colony ◽

Training Data ◽

Practical Recommendation ◽

Preference Change ◽

Change Over Time ◽

Unique Type ◽

Over Time

Recommender systems should be able to handle highly sparse training data that continues to change over time. Among the many solutions, Ant Colony Optimization, as a kind of optimization algorithm modeled on the actions of an ant colony, enjoys the favorable characteristic of being optimal, which has not been easily achieved by other kinds of algorithms. A recent work adopting genetic optimization proposes a collaborative filtering scheme: Ant Collaborative Filtering (ACF), which models the pheromone of ants for a recommender system in two ways: (1) use the pheromone exchange to model the ratings given by users with respect to items; (2) use the evaporation of existing pheromone to model the evolution of users’ preference change over time. This mechanism helps to identify the users and the items most related, even in the case of sparsity, and can capture the drift of user preferences over time. However, it reveals that many users share the same preference over items, which means it is not necessary to initialize each user with a unique type of pheromone, as was done with the ACF. Regarding the sparsity problem, this work takes one step further to improve the Ant Collaborative Filtering’s performance by adding a clustering step in the initialization phase to reduce the dimension of the rate matrix, which leads to the results that K<<#users, where K is the number of clusters, which stands for the maximum number of types of pheromone carried by all users. We call this revised version the Improved Ant Collaborative Filtering (IACF). Experiments are conducted on larger datasets, compared with the previous work, based on three typical recommender systems: (1) movie recommendations, (2) music recommendations, and (3) book recommendations. For movie recommendation, a larger dataset, MoviesLens 10M, was used, instead of MoviesLens 1M. For book recommendation and music recommendation, we used a new dataset that has a much larger size of samples from Douban and NetEase. The results illustrate that our IACF algorithm can better deal with practical recommendation scenarios that handle sparse dataset.

Download Full-text

Determinants of disease activity change over time in Enthesitis related arthritis: effect of structured outcome monitoring and clinical decision support

Pediatric Rheumatology ◽

10.1186/s12969-020-00472-3 ◽

2020 ◽

Vol 18 (1) ◽

Author(s):

Francesca Tirelli ◽

Rui Xiao ◽

Timothy G. Brandon ◽

Jon M. Burnham ◽

Joyce C. Chang ◽

...

Keyword(s):

Decision Support ◽

Disease Activity ◽

Clinical Decision Support ◽

Point Of Care ◽

Clinical Decision ◽

Change Over Time ◽

Enthesitis Related Arthritis ◽

Outcome Monitoring ◽

Care Outcome ◽

Over Time

Abstract Background We aimed to test if standardized point-of-care outcome monitoring and clinical decision support (CDS), as compared to standard care, improves disease activity and patient-reported pain in children with enthesitis-related arthritis (ERA). Methods This was a retrospective cohort study of outcomes of children with ERA after phased implementation of I) standardized outcome monitoring with CDS for polyarticular JIA, and II) CDS for ERA, compared to a pre-intervention group of historical controls. We used multivariable mixed-effects models for repeated measures to test whether implementation phase or other disease characteristics were associated with change over time in disease activity, as measured by the clinical juvenile arthritis disease activity score (cJADAS), and pain. Results One hundred fifty-two ERA patients (41% incident cases) were included with a median age of 14.9 years. Implementation of standardized outcome monitoring or ERA-specific CDS did not result in significant differences in cJADAS or pain over time compared to the pre-intervention cohort. Higher cJADAS at the index visit, pain and more tender entheses were significantly associated with higher cJADAS scores over time (all p < 0.01), while biologic use was associated with lower cJADAS (p = 0.02). Regardless of intervention period, incident ERA cases had a greater rate of cJADAS improvement over time compared to prevalent cases (p < 0.01), but pain persisted over time among both incident and prevalent cases. Conclusions There was no significant effect of point-of-care outcome monitoring or CDS interventions on disease activity or pain over time in children with ERA in this single center study. Future efforts to improve disease outcomes using standardized outcome monitoring and CDS will need to consider the importance of addressing pain as a target in addition to spondyloarthritis-specific disease activity metrics.

Download Full-text