Predicting which documents she will judge relevant, whether based on tenfold cross-validation, or on predicting relevance for 2011 documents based on training on pre-2011 documents, is noticeably more accurate when "maybe" judgments are folded in with "no" judgments than when "maybe" judgments are folded in with "yes" judgments.
Biomedical searchers are often interested in finding the most recent papers, but recency is only one factor that might be used to predict relevance.
Our results are positive when judgments of maybe relevant are converted to not relevant, i.e., as shown in Tables 1 and 2, where results of 75%% accuracy are achieved using libsvm and tenfold cross validation and 63 %, when training on judgments of 2008 2010 documents to predict relevance for 2011 documents.
Of the subset of 60 "ancient LGT" genes which Gophna starred in the HD100 genome as having predicted "predatory relevance", only 4 (7%) were found by BLAST (bd1724, 2297,2671 and 3695) and by RSD analysis these 4 and a further 2 (bd940 and 1872) (10%) were found not to be conserved in Tiberius.
The goal of this study is to show that the words, and their within document and overall frequencies within the collection of reviewed documents, taken from documents judged to be relevant and non-relevant to her information need by a human microbiome researcher, can be used to predict the relevance and non-relevance of additional documents to her information need.
It was found that the researcher's relevance judgments could be used to accurately predict the relevance of additional documents: both using tenfold cross-validation and by training on publications from 2008 2010 and testing on documents from 2011.
We used documents annotated with the relevance labels as input to the machine-learning methods, and we trained the SVM classifier to predict the relevance label for each document and used these predictions for ranking.
In our study we show that relevance feedback from a human microbiome researcher can be used to predict the relevance, for that same researcher, of unseen additional documents.
Our case study has shown that the relevance feedback judgments of a human microbiome researcher can be used to effectively predict the relevance of additional documents.
The assessment is guided by an analytical framework that predicts the relevance and receptiveness of different timber supply chains to current systems of trade-based governance.
