A pattern mining approach for information filtering systems

It is a big challenge to clearly identify the boundary between positive and negative streams for information filtering systems. Several attempts have used negative feedback to solve this challenge; however, there are two issues for using negative relevance feedback to improve the effectiveness of information filtering. The first one is how to select constructive negative samples in order to reduce the space of negative documents. The second issue is how to decide noisy extracted features that should be updated based on the selected negative samples. This paper proposes a pattern mining based approach to select some offenders from the negative documents, where an offender can be used to reduce the side effects of noisy features. It also classifies extracted features (i.e., terms) into three categories: positive specific terms, general terms, and negative specific terms. In this way, multiple revising strategies can be used to update extracted features. An iterative learning algorithm is also proposed to implement this approach on the RCV1 data collection, and substantial experiments show that the proposed approach achieves encouraging performance and the performance is also consistent for adaptive filtering as well.     

Teacher Professional Development and Student Literacy Growth: a Systematic Review and Meta-analysis

This systematic review explores the impact of teacher professional development (PD) on student reading achievement. The first part of the literature evaluates all available existing systematic reviews and meta-analyses of PD intervention studies. No quality reviews of PD and reading specifically (distinct from ‘attainment’) were found. There was a little overlap of studies in existing reviews. The second part of the systematic review focuses on the most recent intervention studies exploring PD and student reading achievement. The results of a meta-analysis of all high-quality studies are presented in the third part of the paper. This analysis showed no strong evidence of publication bias and an effect size for PD on student literacy of g = 0.225. This effect was moderated by the number of hours of PD whereby studies with fewer than 30 h of PD was significant for student reading outcomes (g = 0.367, p < 0.001) but more than 30 PD hours was not significant (g = 0.143, p > .05). Following a Weight of Evidence assessment, analysis showed that nearly all high-quality articles involved shorter PD. Weight of Evidence was a significant moderator, (g = 0.408, p < 0.001 for high-quality studies, g = 0.077, p > 0.5, n.s., for medium quality studies). Our review suggests that only high-quality studies of short teacher PD currently provide evidence of impact on student’s reading achievement.