If you use this lexical database, please cite this paper:

	dos Santos, L. B., Duran, M. S., Hartmann, N. S., Candido Junior, A., Paetzold, G. H.,  Aluísio, S. M. (2017). A Lightweight Regression Method to Infer Psycholinguistic Properties for Brazilian Portuguese. In Text, Speech, and Dialogue: 20th International Conference, TSD 2017, Prague, Czech Republic, August 27-31, 2017. Springer.

	@inproceedings{santos:lightweight:tsd:2017,
	Author = {{dos Santos}, Leandro Borges and Duran, Magali Sanchez and Hartmann, Nathan Siegle, and {Candido Junior}, Arnaldo and Paetzold, Gustavo Henrique and Aluísio, Sandra Maria},
	Booktitle = {International Conference on Text, Speech, and Dialogue},
	Publisher = {Springer},
	Title = {A Lightweight Regression Method to Infer Psycholinguistic Properties for Brazilian Portuguese},
	Year = {2017}}

	Preprint version:
		https://arxiv.org/pdf/1705.07008.pdf


== Contact ==

The author, Leandro Borges dos Santos, can be reached at sborgesleandro@gmail.com

== Fields ==

All lines in the "PB.csv" file (UTF-8), except for the first two header lines, are composed of:

	<Word>	<Simplified grammatical category> <Concretenes>	<Subjective Frequency>	<Imagery>	<AoA>	<Log frequency>	<Frequency>


	The columns <Concretenes>	<Subjective Frequency>	<Imagery>	<AoA> are a floating point value obtained by our regressor.

	The frequency and log frequency is from Corpus Brasileiro.

	<Simplified grammatical category> can be  "a" (adjective), "adv" (adverb), "sf" (fem noum), "sm" (masc noum), "v" (verb).
