From 0e3edc501897bfdac52bfeda6316181b9c4d5ce3 Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Wed, 23 Nov 2022 11:26:36 +0100 Subject: [PATCH 1/2] [Bulk Tag] fixed issue in verb name --- .../criteria/ContainsVerbIgnoreCase.java | 2 +- .../bulktag/criteria/EqualVerbIgnoreCase.java | 2 +- .../criteria/NotContainsVerbIgnoreCase.java | 2 +- .../criteria/NotEqualVerbIgnoreCase.java | 2 +- .../communityconfiguration/tagging_conf.xml | 66 +++++++++---------- 5 files changed, 37 insertions(+), 37 deletions(-) diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/criteria/ContainsVerbIgnoreCase.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/criteria/ContainsVerbIgnoreCase.java index a4a6f5663..501eb51b9 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/criteria/ContainsVerbIgnoreCase.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/criteria/ContainsVerbIgnoreCase.java @@ -3,7 +3,7 @@ package eu.dnetlib.dhp.bulktag.criteria; import java.io.Serializable; -@VerbClass("contains_ignorecase") +@VerbClass("contains_caseinsensitive") public class ContainsVerbIgnoreCase implements Selection, Serializable { private String param; diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/criteria/EqualVerbIgnoreCase.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/criteria/EqualVerbIgnoreCase.java index c5f0ce070..1cd07755c 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/criteria/EqualVerbIgnoreCase.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/criteria/EqualVerbIgnoreCase.java @@ -3,7 +3,7 @@ package eu.dnetlib.dhp.bulktag.criteria; import java.io.Serializable; -@VerbClass("equals_ignorecase") +@VerbClass("equals_caseinsensitive") public class EqualVerbIgnoreCase implements Selection, Serializable { private String param; diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/criteria/NotContainsVerbIgnoreCase.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/criteria/NotContainsVerbIgnoreCase.java index b21be83f0..e12b65a27 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/criteria/NotContainsVerbIgnoreCase.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/criteria/NotContainsVerbIgnoreCase.java @@ -3,7 +3,7 @@ package eu.dnetlib.dhp.bulktag.criteria; import java.io.Serializable; -@VerbClass("not_contains_ignorecase") +@VerbClass("not_contains_caseinsensitive") public class NotContainsVerbIgnoreCase implements Selection, Serializable { private String param; diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/criteria/NotEqualVerbIgnoreCase.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/criteria/NotEqualVerbIgnoreCase.java index c6958a641..c1749621e 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/criteria/NotEqualVerbIgnoreCase.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/criteria/NotEqualVerbIgnoreCase.java @@ -3,7 +3,7 @@ package eu.dnetlib.dhp.bulktag.criteria; import java.io.Serializable; -@VerbClass("not_equals_ignorecase") +@VerbClass("not_equals_caseinsensitive") public class NotEqualVerbIgnoreCase implements Selection, Serializable { private String param; diff --git a/dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/bulktag/communityconfiguration/tagging_conf.xml b/dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/bulktag/communityconfiguration/tagging_conf.xml index 06c57511d..4e580edf5 100644 --- a/dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/bulktag/communityconfiguration/tagging_conf.xml +++ b/dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/bulktag/communityconfiguration/tagging_conf.xml @@ -1193,7 +1193,7 @@ - {"criteria":[{"constraint":[{"verb":"equals_ignorecase","field":"subject","value":"ciencias de la comunicación"}, + {"criteria":[{"constraint":[{"verb":"equals_caseinsensitive","field":"subject","value":"ciencias de la comunicación"}, {"verb":"equals","field":"subject","value":"Miriam"}]}, {"constraint":[{"verb":"equals","field":"subject","value":"miriam"}]}]} @@ -1317,81 +1317,81 @@ opendoar____::358aee4cc897452c00244351e4d91f69 - {"criteria":[{"constraint":[{"verb":"contains_ignorecase","field":"title","value":"COVID-19"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"SARS-CoV-2"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"2019-nCoV"}}]} + {"criteria":[{"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"COVID-19"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"SARS-CoV-2"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"2019-nCoV"}}]} re3data_____::7b0ad08687b2c960d5aeef06f811d5e6 - {"criteria":[{"constraint":[{"verb":"contains_ignorecase","field":"title","value":"COVID-19"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"SARS-CoV-2"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"2019-nCoV"}]}]} + {"criteria":[{"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"COVID-19"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"SARS-CoV-2"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"2019-nCoV"}]}]} driver______::bee53aa31dc2cbb538c10c2b65fa5824 - {"criteria":[{"constraint":[{"verb":"contains_ignorecase","field":"title","value":"COVID-19"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"SARS-CoV-2"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"2019-nCoV"}]}]} + {"criteria":[{"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"COVID-19"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"SARS-CoV-2"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"2019-nCoV"}]}]} openaire____::437f4b072b1aa198adcbc35910ff3b98 - {"criteria":[{"constraint":[{"verb":"contains_ignorecase","field":"title","value":"COVID-19"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"SARS-CoV-2"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"2019-nCoV"}]}]} + {"criteria":[{"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"COVID-19"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"SARS-CoV-2"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"2019-nCoV"}]}]} openaire____::081b82f96300b6a6e3d282bad31cb6e2 - {"criteria":[{"constraint":[{"verb":"contains_ignorecase","field":"title","value":"COVID-19"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"SARS-CoV-2"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"2019-nCoV"}]}]} + {"criteria":[{"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"COVID-19"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"SARS-CoV-2"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"2019-nCoV"}]}]} openaire____::9e3be59865b2c1c335d32dae2fe7b254 - {"criteria":[{"constraint":[{"verb":"contains_ignorecase","field":"title","value":"COVID-19"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"SARS-CoV-2"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"2019-nCoV"}]}]} + {"criteria":[{"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"COVID-19"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"SARS-CoV-2"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"2019-nCoV"}]}]} opendoar____::8b6dd7db9af49e67306feb59a8bdc52c - {"criteria":[{"constraint":[{"verb":"contains_ignorecase","field":"title","value":"COVID-19"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"SARS-CoV-2"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"2019-nCoV"}]}]} + {"criteria":[{"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"COVID-19"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"SARS-CoV-2"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"2019-nCoV"}]}]} share_______::4719356ec8d7d55d3feb384ce879ad6c - {"criteria":[{"constraint":[{"verb":"contains_ignorecase","field":"title","value":"COVID-19"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"SARS-CoV-2"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"2019-nCoV"}]}]} + {"criteria":[{"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"COVID-19"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"SARS-CoV-2"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"2019-nCoV"}]}]} share_______::bbd802baad85d1fd440f32a7a3a2c2b1 - {"criteria":[{"constraint":[{"verb":"contains_ignorecase","field":"title","value":"COVID-19"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"SARS-CoV-2"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"2019-nCoV"}]}]} + {"criteria":[{"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"COVID-19"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"SARS-CoV-2"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"2019-nCoV"}]}]} opendoar____::6f4922f45568161a8cdf4ad2299f6d23 - {"criteria":[{"constraint":[{"verb":"contains_ignorecase","field":"title","value":"COVID-19"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"SARS-CoV-2"}]}, - {"constraint":[{"verb":"contains_ignorecase","field":"title","value":"2019-nCoV"}]}]} + {"criteria":[{"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"COVID-19"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"SARS-CoV-2"}]}, + {"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"2019-nCoV"}]}]} re3data_____::7980778c78fb4cf0fab13ce2159030dc - {"criteria":[{"constraint":[{"verb":"contains_ignorecase","field":"title","value":"SARS-CoV-2"}]},{"constraint":[{"verb":"contains_ignorecase","field":"title","value":"COVID-19"}]},{"constraint":[{"verb":"contains_ignorecase","field":"title","value":"2019-nCov"}]}]} + {"criteria":[{"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"SARS-CoV-2"}]},{"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"COVID-19"}]},{"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"2019-nCov"}]}]} re3data_____::978378def740bbf2bfb420de868c460b - {"criteria":[{"constraint":[{"verb":"contains_ignorecase","field":"title","value":"SARS-CoV-2"}]},{"constraint":[{"verb":"contains_ignorecase","field":"title","value":"COVID-19"}]},{"constraint":[{"verb":"contains_ignorecase","field":"title","value":"2019-nCov"}]}]} + {"criteria":[{"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"SARS-CoV-2"}]},{"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"COVID-19"}]},{"constraint":[{"verb":"contains_caseinsensitive","field":"title","value":"2019-nCov"}]}]} From 90c8f9cb6178cc7d257d4f3000e48d734a6c2b5d Mon Sep 17 00:00:00 2001 From: Alessia Bardi Date: Wed, 23 Nov 2022 12:18:44 +0100 Subject: [PATCH 2/2] tests for EOSC Future --- .../provision/IndexRecordTransformerTest.java | 14 + .../eosc-future/software-justthink-claim.xml | 305 +++++++++++++ .../eosc-future/software-justthink.xml | 429 ++++++++++++++++++ 3 files changed, 748 insertions(+) create mode 100644 dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/eosc-future/software-justthink-claim.xml create mode 100644 dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/eosc-future/software-justthink.xml diff --git a/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/IndexRecordTransformerTest.java b/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/IndexRecordTransformerTest.java index e0fbb2a2f..17c3cdb30 100644 --- a/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/IndexRecordTransformerTest.java +++ b/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/IndexRecordTransformerTest.java @@ -128,6 +128,20 @@ public class IndexRecordTransformerTest { testRecordTransformation(record); } + @Test + public void testForEOSCFutureSoftwareNotebook() throws IOException, TransformerException { + final String record = IOUtils + .toString(getClass().getResourceAsStream("eosc-future/software-justthink.xml")); + testRecordTransformation(record); + } + + @Test + public void testForEOSCFutureSoftwareNotebookClaim() throws IOException, TransformerException { + final String record = IOUtils + .toString(getClass().getResourceAsStream("eosc-future/software-justthink-claim.xml")); + testRecordTransformation(record); + } + @Test void testDoiUrlNormalization() throws MalformedURLException { diff --git a/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/eosc-future/software-justthink-claim.xml b/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/eosc-future/software-justthink-claim.xml new file mode 100644 index 000000000..02089bb30 --- /dev/null +++ b/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/eosc-future/software-justthink-claim.xml @@ -0,0 +1,305 @@ + + +
+ od______2659::3801993ea8f970cfc991277160edf277 + 2022-08-08T03:06:13Z + under curation + +
+ + + + JUSThink + Alignment Analysis + Norman, Utku + Dinkar, Tanvi + Bruno, Barbara + Clavel, Chloé + + + + +

+ 1. Description +

+

This repository contains tools to automatically analyse how + participants align their use of task-specific referents in their + dialogue and actions for a collaborative learning activity, and how + it relates to the task success (i.e. their learning + outcomes and task performance).

+

As a use case, it processes data from a collaborative problem solving + activity named JUSThink [1, 2], i.e. + JUSThink Dialogue and Actions Corpus data set that is available from the + Zenodo Repository, DOI: 10.5281/zenodo.4627104, and reproduces the results and figures + in [3].

+

In brief:

+
    +
  1. JUSThink Dialogue and Actions Corpus contains + transcripts, event logs, and test responses of children aged 9 + through 12, as they participate in the JUSThink activity [1, 2] + in pairs of two, to solve a problem on graphs together.
    2. +
  2. The JUSThink activity and its study is first + described in [1], and elaborated with findings concerning the link + between children's learning, performance in the activity, and + perception of self, the other and the robot in [2].
    3. +
  3. Alignment analysis in our work [3] studies the participants' use of + expressions that are related to the task at hand, their follow up + actions of these expressions, and how it links to task success.
    4. +
+

+ 2. Publications +

+

If you use this work in an academic context, please cite the following + publications:

+
    +
  • +

    Norman*, U., Dinkar*, T., Bruno, B., & Clavel, C. (2022). + Studying Alignment in a Collaborative Learning Activity via + Automatic Methods: The Link Between What We Say and Do. Dialogue + & Discourse, 13(2), 1 - ;48. *Contributed equally to this + work. https://doi.org/10.5210/dad.2022.201

    +
    • +
  • +

    Norman, U., Dinkar, T., Bruno, B., & Clavel, C. (2021). + JUSThink Alignment Analysis. In Dialogue & Discourse + (v1.0.0, Vol. 13, Number 2, pp. 1 - ;48). Zenodo. https://doi.org/10.5281/zenodo.4675070

    +
    • +
+

+ 3. Content +

+

The tools provided in this repository consists of 7 Jupyter Notebooks + written in Python 3, and two additional external tools utilised by the + notebooks.

+

+ 3.1. Jupyter Notebooks +

+

We highlight that the notebooks up until the last (i.e. to test the + hypotheses (tools/7_test_the_hypotheses.ipynb)) present a general + pipeline to process event logs, test responses and transcripts to + extract measures of task performance, learning outcomes, and measures of + alignment.

+
    +
  1. Extract task performance (and other features) from the logs + (tools/1_extract_performance_and_other_features_from_logs.ipynb): + Extracts various measures of task behaviour from the logs, at + varying granularities of the activity (i.e. the whole corpus, task, + attempt, and turn levels). In later notebooks, we focus on one of + the features to estimate the task performance of a team: (minimum) + error.
    2. +
  2. Extract learning outcomes from the test responses + (tools/2_extract_learning_gain_from_test_responses.ipynb): Extracts + measures of learning outcomes from the responses to the pre-test and + the post-test. In later notebooks, we focus on one of the features + to estimate the learning outcome of a team: relative learning gain + [4]
    3. +
  3. Select and visualise a subset of teams for + transcription + (tools/3_visualise_transcribed_teams.ipynb): Visualises the + transcribed teams among the other teams in the feature space spanned + by task performance and learning outcome, as well as the + distribution of their number of attempts and turns.
    4. +
  4. Extract routines from transcripts + (tools/4_extract_routines_from_transcripts.ipynb) (uses dialign to + extract routines): Extracts routines of referring expressions that + are "fixed", i.e. become shared or established amongst + interlocutors.
    5. +
  5. Combine transcripts with logs + (tools/5_construct_the_corpus_by_combining_transcripts_with_logs.ipynb): + Merges transcripts with event logs to have a combined dialogue and + actions corpus, to be processed e.g. to detect follow-up + actions.
    6. +
  6. Recognise instructions and detect follow-up actions + (tools/6_recognise_instructions_detect_follow-up_actions.ipynb): + Extracts verbalised instruction such as "connect Mount Basel to + Montreux", and pairs them with the follow-up action that may + match (e.g. if the other connects Basel to Montreux) or + mismatch (e.g. if the other connects Basel to + Neuchatel) with the instruction.
    7. +
  7. Test the hypotheses in [3] (tools/7_test_the_hypotheses.ipynb) (uses + effsize to estimate effect size, specifically + Cliff's Delta): Considers each research questions and hypotheses + studied in [3] and generates the results in [3].
    8. +
+

+ 3.2. External Tools +

+
    +
  1. dialign + tool to extract routines, specifically Release 1.0 from dialign-1.0.zip:\n It extracts routine expressions that are + "shared" among the participants from transcripts. \n It is + used as an external module (in accordance with its CeCILL-B License, + see License).
    2. +
  2. effsize tool to compute estimators of effect + size.\n We specifically use it to compute Cliff's Delta, which + quantifies the amount difference between two groups of observations, + by computing the Cliff's Delta statistic.\n It is taken from + project DABEST (see License).
    3. +
+

+ 4. Research Questions and Hypotheses in [3] +

+
    +
  • RQ1 Lexical alignment: How do the interlocutors + use expressions related to the task? Is this associated + with task success?
      +
    • H1.1: Task-specific referents become + routine early for more successful teams.
      • +
    • H1.2: Hesitation phenomena are more likely + to occur in the vicinity of priming and establishment of + task-specific referents for more successful teams.
      • +
    +
    • +
  • RQ2 Behavioural alignment: How do the interlocutors + follow up these expressions with actions? Is this + associated with task success?
      +
    • H2.1: Instructions are more likely to be + followed by a corresponding action early in the dialogue for + more successful teams.
      • +
    • H2.2: When instructions are followed by a + corresponding or a different action, the action is more + likely to be in the vicinity of information management + phenomena for more successful teams.
      • +
    +
    • +
+

The RQs and Hs are addressed in the notebook for testing the hypotheses + (i.e. tools/7_test_the_hypotheses.ipynb).

+

+ Acknowledgements +

+

This project has received funding from the European Union's Horizon + 2020 research and innovation programme under grant agreement No 765955. + Namely, the ANIMATAS Project.

+

+ License +

+

The whole package is under MIT License, see the LICENSE + file.

+

Classes under the tools/effsize package were taken from + project DABEST, Copyright 2016-2020 Joses W. Ho. + These classes are licensed under the BSD 3-Clause Clear License. See + tools/effsize/LICENSE file for additional + details.

+

Classes under the tools/dialign-1.0 package were taken + from project dialign. These classes are licensed under the + CeCILL-B License. This package is used as an "external + module", see tools/dialign-1.0/LICENSE.txt for + additional details.

+ + + + + Zenodo + + + + + + + + + + + + + + + + + + + oai:zenodo.org:4675070 + + oai:zenodo.org:4675070 + 10.5281/zenodo.4675070 + + + + false + false + 0.9 + + + + + + corda__h2020::c4515ebef538a734cf11f795347f5dac + 765955 + ANIMATAS + Advancing intuitive human-machine interaction with human-like + social capabilities for education in schools + + + + ec__________::EC::H2020 + + + + + + + + + + + + + https://zenodo.org/record/4675070 + + + + + + + + diff --git a/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/eosc-future/software-justthink.xml b/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/eosc-future/software-justthink.xml new file mode 100644 index 000000000..9c0f4ea7d --- /dev/null +++ b/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/eosc-future/software-justthink.xml @@ -0,0 +1,429 @@ + + +
+ doi_dedup___::c054151b6a8c4f41c7acf160651a6503 + 2022-10-13T00:15:44+0000 + 2022-10-13T07:44:29.152Z +
+ + + + + + oai:zenodo.org:4675070 + 50|od______2659::3801993ea8f970cfc991277160edf277 + oai:zenodo.org:6974562 + 50|od______2659::9c87ff4a5e7710052b873088e7265072 + 10.5281/zenodo.4675069 + 10.5281/zenodo.4675070 + 10.5281/zenodo.6974562 + 10.5281/zenodo.4675069 + + + + + + JUSThink Alignment + Analysis + + Norman, Utku + Dinkar, Tanvi + Bruno, Barbara + Clavel, Chloé + 2022-08-08 + <strong>1. Description</strong> This repository + contains<strong> tools to automatically analyse how participants align + their use of task-specific referents in their dialogue and actions for a + collaborative learning activity, and how it relates to the task + success</strong> (i.e. their learning outcomes and task performance). As + a use case, it processes data from a collaborative problem solving activity + named JUSThink [1, 2], i.e. JUSThink Dialogue and Actions Corpus data set that + is available from the Zenodo Repository, DOI: 10.5281/zenodo.4627104, and + reproduces the results and figures in [3]. In brief: <strong>JUSThink + Dialogue and Actions Corpus</strong> contains transcripts, event logs, + and test responses of children aged 9 through 12, as they participate in the + JUSThink activity [1, 2] in pairs of two, to solve a problem on graphs together. + <strong>The JUSThink activity and its study</strong> is first + described in [1], and elaborated with findings concerning the link between + children's learning, performance in the activity, and perception of self, the + other and the robot in [2]. <strong>Alignment analysis in our work + [3]</strong> studies the participants' use of expressions that are + related to the task at hand, their follow up actions of these expressions, and + how it links to task success. <strong>Changes in Release + v1.1.0:</strong> updated with the publication information, finalized + paper structure, research questions and hypotheses as in the published article: + U. Norman*<em>, </em>T. Dinkar*, B. Bruno, and C. Clavel, + "Studying Alignment in a Collaborative Learning Activity via Automatic Methods: + The Link Between What We Say and Do," Dialogue & Discourse, 13(2), + 1–48. *Contributed equally to this work. 10.5210/dad.2022.201. + <strong>Full Changelog:</strong> + https://github.com/chili-epfl/justhink-alignment-analysis/compare/v1.0.0...v1.1.0 + <strong>2. Publications</strong> If you use this work in an + academic context, please cite the following publications: Norman*, U., Dinkar*, + T., Bruno, B., & Clavel, C. (2022). Studying Alignment in a + Collaborative Learning Activity via Automatic Methods: The Link Between What We + Say and Do. Dialogue & Discourse, 13(2), 1–48. *Contributed equally + to this work. https://doi.org/10.5210/dad.2022.201 Norman, U., Dinkar, T., + Bruno, B., & Clavel, C. (2021). JUSThink Alignment Analysis. In + Dialogue & Discourse (v1.1.0, Vol. 13, Number 2, pp. 1–48). Zenodo. + https://doi.org/10.5281/zenodo.6974562 <strong>3. Content</strong> + The tools provided in this repository consists of 7 Jupyter Notebooks written in + Python 3, and two additional external tools utilised by the notebooks. + <strong>3.1. Jupyter Notebooks</strong> We highlight that the + notebooks up until the last (i.e. to test the hypotheses + (tools/7_test_the_hypotheses.ipynb)) present a general pipeline to process event + logs, test responses and transcripts to extract measures of task performance, + learning outcomes, and measures of alignment. <strong>Extract task + performance (and other features) from the logs + </strong>(tools/1_extract_performance_and_other_features_from_logs.ipynb): + Extracts various measures of task behaviour from the logs, at varying + granularities of the activity (i.e. the whole corpus, task, attempt, and turn + levels). In later notebooks, we focus on one of the features to estimate the + task performance of a team: (minimum) error. <strong>Extract learning + outcomes from the test responses</strong> + (tools/2_extract_learning_gain_from_test_responses.ipynb): Extracts measures of + learning outcomes from the responses to the pre-test and the post-test. In later + notebooks, we focus on one of the features to estimate the learning outcome of a + team: relative learning gain [4] <strong>Select and visualise a subset of + teams for transcription</strong> + (tools/3_visualise_transcribed_teams.ipynb): Visualises the transcribed teams + among the other teams in the feature space spanned by task performance and + learning outcome, as well as the distribution of their number of attempts and + turns. <strong>Extract routines from transcripts</strong> + (tools/4_extract_routines_from_transcripts.ipynb) (uses dialign to extract + routines): Extracts routines of referring expressions that are "fixed", i.e. + become shared or established amongst interlocutors. <strong>Combine + transcripts with logs</strong> + (tools/5_construct_the_corpus_by_combining_transcripts_with_logs.ipynb): Merges + transcripts with event logs to have a combined dialogue and actions corpus, to + be processed e.g. to detect follow-up actions. <strong>Recognise + instructions and detect follow-up actions</strong> + (tools/6_recognise_instructions_detect_follow-up_actions.ipynb): Extracts + verbalised instruction such as "connect Mount Basel to Montreux", and pairs them + with the follow-up action that may <em>match</em> (e.g. if the + other connects Basel to Montreux) or <em>mismatch</em> (e.g. if + the other connects Basel to Neuchatel) with the instruction. <strong>Test + the hypotheses </strong>in [3] (tools/7_test_the_hypotheses.ipynb) (uses + <strong>effsize</strong> to estimate effect size, specifically + Cliff's Delta): Considers each research questions and hypotheses studied in [3] + and generates the results in [3]. <strong>3.2. External + Tools</strong> <strong>dialign tool</strong> to extract + routines, specifically Release 1.0 from dialign-1.0.zip:<br> It extracts + routine expressions that are "shared" among the participants from transcripts. + <br> It is used as an external module (in accordance with its CeCILL-B + License, see <strong>License</strong>). <strong>effsize + tool</strong> to compute estimators of effect size.<br> We + specifically use it to compute Cliff's Delta, which quantifies the amount + difference between two groups of observations, by computing the Cliff's Delta + statistic.<br> It is taken from project DABEST (see + <strong>License</strong>). <strong>4. Research Questions + and Hypotheses in [3]</strong> <strong>RQ1 Lexical + alignment</strong>: How do the interlocutors <em>use</em> + expressions related to the task? Is this associated with task success? + <strong>H1.1</strong>: Task-specific referents become routine + early for more successful teams. <strong>H1.2</strong>: Hesitation + phenomena are more likely to occur in the vicinity of priming and establishment + of task-specific referents for more successful teams. <strong>RQ2 + Behavioural alignment</strong>: How do the interlocutors + <em>follow up</em> these expressions with actions? Is this + associated with task success? <strong>H2.1</strong>: Instructions + are more likely to be followed by a corresponding action early in the dialogue + for more successful teams. <strong>H2.2</strong>: When + instructions are followed by a corresponding or a different action, the action + is more likely to be in the vicinity of information management phenomena for + more successful teams. The RQs and Hs are addressed in the notebook for testing + the hypotheses (i.e. tools/7_test_the_hypotheses.ipynb). + <strong>Acknowledgements</strong> This project has received + funding from the European Union's Horizon 2020 research and innovation programme + under grant agreement No 765955. Namely, the ANIMATAS Project. + <strong>License</strong> The whole package is under MIT License, + see the <strong>LICENSE</strong> file. Classes under the + <strong>tools/effsize</strong> package were taken from project + <strong>DABEST</strong>, Copyright 2016-2020 Joses W. Ho. These + classes are licensed under the BSD 3-Clause Clear License. See + <strong>tools/effsize/LICENSE</strong> file for additional + details. Classes under the <strong>tools/dialign-1.0</strong> + package were taken from project <strong>dialign</strong>. These + classes are licensed under the CeCILL-B License. This package is used as an + "external module", see<strong> + tools/dialign-1.0/LICENSE.txt</strong> for additional + details. + {"references": ["[1] J. Nasir, U. Norman, B. Bruno, and P. Dillenbourg, + \"You Tell, I Do, and We Swap until we Connect All the Gold Mines!,\" ERCIM + News, vol. 2020, no. 120, 2020, [Online]. Available: + https://ercim-news.ercim.eu/en120/special/you-tell-i-do-and-we-swap-until-we-connect-all-the-gold-mines", + "[2] J. Nasir*, U. Norman*, B. Bruno, and P. Dillenbourg, \"When Positive + Perception of the Robot Has No Effect on Learning,\" in 2020 29th IEEE + International Conference on Robot and Human Interactive Communication (RO-MAN), + Aug. 2020, pp. 313\u2013320, doi: 10.1109/RO-MAN47096.2020.9223343", "[3] U. + Norman*, T. Dinkar*, B. Bruno, and C. Clavel, \"Studying Alignment in a + Collaborative Learning Activity via Automatic Methods: The Link Between What We + Say and Do,\" Dialogue & Discourse, vol. 13, no. 2, pp. 1\u201348, + Aug. 2022, doi: 10.5210/dad.2022.201.", "[4] M. Sangin, G. Molinari, M.-A. + N\u00fcssli, and P. Dillenbourg, \"Facilitating peer knowledge modeling: Effects + of a knowledge awareness tool on collaborative learning outcomes and + processes,\"\" Computers in Human Behavior, vol. 27, no. 3, pp. 1059\u20131067, + May 2011, doi: 10.1016/j.chb.2010.05.032."]} + alignment + situated + dialogue + collaborative + learning + spontaneous + speech + disfluency + mutual + understanding + + 2021-04-09 + 2022-08-08 + Zenodo + + + + + + + + + + + true + false + 0.8 + dedup-result-decisiontree-v3 + + + + + doi_dedup___::ae235765bbc422195a6c9f632b2d77eb + + 2104.04429 + + arXiv + + 2022-08-05 + Studying + Alignment in a Collaborative Learning Activity via Automatic Methods: + The Link Between What We Say and Do + + + 10.48550/arxiv.2104.04429 + 10.5210/dad.2022.201 + + + corda__h2020::c4515ebef538a734cf11f795347f5dac + Advancing intuitive human-machine interaction with human-like social + capabilities for education in schools + 765955 + + + ec__________::EC::H2020 + ec__________::EC::H2020::MSCA-ITN-ETN + + ANIMATAS + + + doi_dedup___::0a6314b0ed275d915f5b57a259375691 + 2021-03-22 + Zenodo + 10.5281/zenodo.4627104 + JUSThink Dialogue and Actions Corpus + 10.5281/zenodo.4627103 + + + + + + + Zenodo + 10.5281/zenodo.4675070 + JUSThink Alignment Analysis + 2021-04-09 + + + + 2022-08-08 + Zenodo + 10.5281/zenodo.6974562 + + JUSThink Alignment Analysis (v1.1.0) + + + JUSThink + Alignment Analysis (v1.1.0) + 2022-08-08 + Zenodo + 10.5281/zenodo.4675069 + + + + + + + 2022-08-08 + + 10.5281/zenodo.4675069 + + https://opensource.org/licenses/MIT + + https://doi.org/10.5281/zenodo.4675069 + + + + + + + 2022-08-08 + + 10.5281/zenodo.6974562 + + https://opensource.org/licenses/MIT + + https://doi.org/10.5281/zenodo.6974562 + + + + + + + 2021-04-09 + + 10.5281/zenodo.4675070 + + https://opensource.org/licenses/MIT + + https://doi.org/10.5281/zenodo.4675070 + + + + + + + +