diff --git a/docs/source/bibliography.bib b/docs/source/bibliography.bib index 8ba08daa0..4c1a1007c 100644 --- a/docs/source/bibliography.bib +++ b/docs/source/bibliography.bib @@ -36,11 +36,11 @@ @misc{JuDo1000 } @misc{potec, - author = {Jäger, Lena A. and Haller, Patrick and Jakobi, Deborah Noemie}, - title = {{Potsdam Textbook Corpus}}, - year = {2021}, - pages = {}, - doi = {10.17605/OSF.IO/DN5HP}, + url = {\url{https://github.com/DiLi-Lab/PoTeC}}, + author = {Jakobi, Deborah N. and Kern, Thomas and Reich, David R. and Haller, Patrick and J\"ager, Lena A.}, + title = {{PoTeC}: A {German} Naturalistic Eye-tracking-while-reading Corpus}, + year = {2024}, + note = {under review}, } @article{SalvucciGoldberg2000, diff --git a/src/pymovements/datasets/gaze_graph.py b/src/pymovements/datasets/gaze_graph.py index 24f003177..c597ebb41 100644 --- a/src/pymovements/datasets/gaze_graph.py +++ b/src/pymovements/datasets/gaze_graph.py @@ -88,7 +88,7 @@ class GazeGraph(DatasetDefinition): >>> >>> dataset = pm.Dataset("GazeGraph", path='data/GazeGraph') - Download the dataset resources resources: + Download the dataset resources: >>> dataset.download()# doctest: +SKIP diff --git a/src/pymovements/datasets/gaze_on_faces.py b/src/pymovements/datasets/gaze_on_faces.py index 35da980a6..204f52633 100644 --- a/src/pymovements/datasets/gaze_on_faces.py +++ b/src/pymovements/datasets/gaze_on_faces.py @@ -86,7 +86,7 @@ class GazeOnFaces(DatasetDefinition): >>> >>> dataset = pm.Dataset("GazeOnFaces", path='data/GazeOnFaces') - Download the dataset resources resources: + Download the dataset resources: >>> dataset.download()# doctest: +SKIP diff --git a/src/pymovements/datasets/gazebase.py b/src/pymovements/datasets/gazebase.py index cb79e343c..4da6643fc 100644 --- a/src/pymovements/datasets/gazebase.py +++ b/src/pymovements/datasets/gazebase.py @@ -90,7 +90,7 @@ class GazeBase(DatasetDefinition): >>> >>> dataset = pm.Dataset("GazeBase", path='data/GazeBase') - Download the dataset resources resources: + Download the dataset resources: >>> dataset.download()# doctest: +SKIP diff --git a/src/pymovements/datasets/gazebasevr.py b/src/pymovements/datasets/gazebasevr.py index 5065aad34..e0ce44910 100644 --- a/src/pymovements/datasets/gazebasevr.py +++ b/src/pymovements/datasets/gazebasevr.py @@ -91,7 +91,7 @@ class GazeBaseVR(DatasetDefinition): >>> >>> dataset = pm.Dataset("GazeBaseVR", path='data/GazeBaseVR') - Download the dataset resources resources: + Download the dataset resources: >>> dataset.download()# doctest: +SKIP diff --git a/src/pymovements/datasets/hbn.py b/src/pymovements/datasets/hbn.py index 47c39f96d..bb49a1a6a 100644 --- a/src/pymovements/datasets/hbn.py +++ b/src/pymovements/datasets/hbn.py @@ -85,7 +85,7 @@ class HBN(DatasetDefinition): >>> >>> dataset = pm.Dataset("HBN", path='data/HBN') - Download the dataset resources resources: + Download the dataset resources: >>> dataset.download()# doctest: +SKIP diff --git a/src/pymovements/datasets/judo1000.py b/src/pymovements/datasets/judo1000.py index 3f232bbe8..3c5143ef7 100644 --- a/src/pymovements/datasets/judo1000.py +++ b/src/pymovements/datasets/judo1000.py @@ -84,7 +84,7 @@ class JuDo1000(DatasetDefinition): >>> >>> dataset = pm.Dataset("JuDo1000", path='data/JuDo1000') - Download the dataset resources resources: + Download the dataset resources: >>> dataset.download()# doctest: +SKIP diff --git a/src/pymovements/datasets/potec.py b/src/pymovements/datasets/potec.py index afb0d2a8b..399597b1d 100644 --- a/src/pymovements/datasets/potec.py +++ b/src/pymovements/datasets/potec.py @@ -36,20 +36,23 @@ class PoTeC(DatasetDefinition): """PoTeC dataset :cite:p:`potec`. - The Potsdam Textbook Corpus (PoTeC) is a corpus of eye-tracking-while-reading data where - participants (N=75) read a series of German short texts taken from college level textbooks - of physics and biology. The experiments were conducted within a 2x2 fully-crossed factorial - design with the reader’s expertise (advanced vs beginner) and major (physics vs biology) as - factors. Reading comprehension was assessed using text comprehension questions. Moreover, - background questions that required additional knowledge beyond the presented text tested the - general domain knowledge. - The repository contains the eye-movement data (1000 Hz, right eye monocular) as well as the - stimulus text data with extensive linguistic feature annotations at the sub-lexical, - lexical und supra-lexical level. Therefore, the PoTeC is ideal for studying cognitive - processes related to sentence comprehension at all linguistic levels (e.g. lexical, - syntactic, discourse) as well as higher-level text comprehension. - - Check the respective `repository `_ for details. + The Potsdam Textbook Corpus (PoTeC) is a naturalistic eye-tracking-while-reading + corpus containing data from 75 participants reading 12 scientific texts. + PoTeC is the first naturalistic eye-tracking-while-reading corpus that contains + eye-movements from domain-experts as well as novices in a within-participant + manipulation: It is based on a 2×2×2 fully-crossed factorial design which includes + the participants' level of study and the participants' discipline of study as + between-subject factors and the text domain as a within-subject factor. The + participants' reading comprehension was assessed by a series of text comprehension + questions and their domain knowledge was tested by text-independent + background questions for each of the texts. The materials are annotated for a + variety of linguistic features at different levels. We envision PoTeC to be used + for a wide range of studies including but not limited to analyses of expert and + non-expert reading strategies. + + The corpus and all the accompanying data at all + stages of the preprocessing pipeline and all code used to preprocess the data are + made available via `GitHub. `_ Attributes ---------- @@ -91,7 +94,7 @@ class PoTeC(DatasetDefinition): >>> >>> dataset = pm.Dataset("PoTeC", path='data/PoTeC') - Download the dataset resources resources: + Download the dataset resources: >>> dataset.download()# doctest: +SKIP @@ -113,7 +116,7 @@ class PoTeC(DatasetDefinition): { 'resource': 'tgd9q/', 'filename': 'PoTeC.zip', - 'md5': '7780904bf7b18ba7d30a811174750db3', + 'md5': 'cffd45039757c3777e2fd130e5d8a2ad', }, ) diff --git a/src/pymovements/datasets/sb_sat.py b/src/pymovements/datasets/sb_sat.py index 2587a4a49..565ba45fe 100644 --- a/src/pymovements/datasets/sb_sat.py +++ b/src/pymovements/datasets/sb_sat.py @@ -84,7 +84,7 @@ class SBSAT(DatasetDefinition): >>> >>> dataset = pm.Dataset("SBSAT", path='data/SBSAT') - Download the dataset resources resources: + Download the dataset resources: >>> dataset.download()# doctest: +SKIP diff --git a/src/pymovements/datasets/toy_dataset.py b/src/pymovements/datasets/toy_dataset.py index c8900c023..a36d2984c 100644 --- a/src/pymovements/datasets/toy_dataset.py +++ b/src/pymovements/datasets/toy_dataset.py @@ -82,7 +82,7 @@ class ToyDataset(DatasetDefinition): >>> >>> dataset = pm.Dataset("ToyDataset", path='data/ToyDataset') - Download the dataset resources resources: + Download the dataset resources: >>> dataset.download()# doctest: +SKIP diff --git a/src/pymovements/datasets/toy_dataset_eyelink.py b/src/pymovements/datasets/toy_dataset_eyelink.py index 265a451e3..fc425d50a 100644 --- a/src/pymovements/datasets/toy_dataset_eyelink.py +++ b/src/pymovements/datasets/toy_dataset_eyelink.py @@ -83,7 +83,7 @@ class ToyDatasetEyeLink(DatasetDefinition): >>> >>> dataset = pm.Dataset("ToyDatasetEyeLink", path='data/ToyDatasetEyeLink') - Download the dataset resources resources: + Download the dataset resources: >>> dataset.download()# doctest: +SKIP