id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_a5ddewjbvzcq5el6oio7lh6jju	Colm Clancy	Spatial Bayesian hierarchical modelling of extreme sea states	2016.0	31	.pdf	application/pdf	7167	655	54	Title Systems in Language: Text Analysis of Government Reports of the Irish Industrial School word embedding to compile domain-specific semantic lexicons for feature extraction Keywords: text analysis, text classification, machine learning, industrial schools, child abuse distant reading methodology whereby word embedding is used to compile domainspecific semantic lexicons for feature extraction to enable machine learning classifiers Annotating excerpts of the Ryan Report based on their semantic content enabled the content of text in the Ryan Report and extracting given categories of information. to find terms in the Ryan Report that were semantically similar to a given set of seed classification model using 100 example paragraphs based on a bag-of-words feature set. Witness Testimony Reporting Verbs: domain specific semantic lexicon The results showed that using word embedding to generate semantic lexicons for feature abuse paragraphs the words in the semantic lexicons were the sole features used.	./cache/work_a5ddewjbvzcq5el6oio7lh6jju.pdf	./txt/work_a5ddewjbvzcq5el6oio7lh6jju.txt