Social Sciences and Digital Humanities Archive

Metrics

71,780 Downloads

Welcome to SODHA, the Belgian federal data archive for social sciences and the digital humanities!

Here you can find and deposit social science and digital humanities data in reusable form. Published datasets receive a DOI, making them citable like other types of publications. SODHA promotes open data by enabling reuse of research data and by safely preserving datasets in the long term.

SODHA is the Belgian service provider in the Consortium of European Social Science Data Archives (CESSDA) and is hosted by the State Archives of Belgium. SODHA was built with the help of DEMO (UCLouvain) and Interface Demography (VUB).

You can consult the SODHA Guide here, and you can read our policies here.

Want to learn more about SODHA? Consult our brochure or our presentation on the State Archives' website.

If you have any question, you can contact us at sodha@arch.be.

State Archives of Belgium

Belgian Archives for Social Sciences

Royal Library of Belgium

The Social Study

NICC-INCC

Royal Museums of Fine Arts

Featured Dataverses

In order to use this feature you must have at least one published dataverse.

Publish Dataverse

Are you sure you want to publish your dataverse? Once you do so it must remain published.

Publish Dataverse

This dataverse cannot be published because the dataverse it is in has not been published.

Delete Dataverse

Are you sure you want to delete your dataverse? You cannot undelete this dataverse.

91 to 100 of 4,202 Results

length_summary.tab Aug 25, 2026 - Replication Data for: From nineteenth-century letters to entities: "a NER pipeline for French correspondence and its methodological lessons" - Article for Digital Humanities Benelux Journal Tabular Data - 533 B - 5 Variables, 9 Observations - UNF:6:XKylVdddSgIVxmbYCdrnFg== Summary statistics describing the distribution of document subword lengths in the evaluation corpus splitsand their relationship to model performance. Used to assess the number of letters affected by preprocessing.
navez_gs_preprocessed-2.csv Aug 25, 2026 - Replication Data for: From nineteenth-century letters to entities: "a NER pipeline for French correspondence and its methodological lessons" - Article for Digital Humanities Benelux Journal Comma Separated Values - 1015.3 KB - MD5: 0469ba07b6aa2663770de059d36ef03f Preprocessed version of the manually annotated corpus after cleaning and conversion from Label Studio. Contains token- and entity-level information used for model training and evaluation.
navez_gs_preprocessed-2.pkl Aug 25, 2026 - Replication Data for: From nineteenth-century letters to entities: "a NER pipeline for French correspondence and its methodological lessons" - Article for Digital Humanities Benelux Journal Unknown - 33.0 MB - MD5: 3a11affcc28d1dc3ac86f185c3f089a2 Python pickle version of the preprocessed gold-standard corpus, preserving data structures used directly in the notebooks.
Navez_ner_finetuning_weightedcrossentropy.ipynb Aug 25, 2026 - Replication Data for: From nineteenth-century letters to entities: "a NER pipeline for French correspondence and its methodological lessons" - Article for Digital Humanities Benelux Journal Jupyter Notebook - 4.6 MB - MD5: 8c2912db3ec1743bd4c24c1103a01c99 Notebook for fine-tuning and evaluating French transformer-based models for Named Entity Recognition on the Navez correspondence. It implements the experiments with CamemBERT, CamemBERTav2, D'AlemBERT and Europeana BERT, including weighted cross-entropy training, hyperparameter o...
navez_spacy_custom_trained_evalall-2.csv Aug 25, 2026 - Replication Data for: From nineteenth-century letters to entities: "a NER pipeline for French correspondence and its methodological lessons" - Article for Digital Humanities Benelux Journal Comma Separated Values - 424 B - MD5: 2431b25f16ced713f3f94efd19eede8d Overall evaluation metrics for the custom-trained spaCy model, including the four project-specific entity types introduced during fine-tuning. Reports precision, recall and F1 under the Nervaluate evaluation scenarios.
navez_spacy_custom_trained_evalall_no_dk-2.tab Aug 25, 2026 - Replication Data for: From nineteenth-century letters to entities: "a NER pipeline for French correspondence and its methodological lessons" - Article for Digital Humanities Benelux Journal Tabular Data - 462 B - 1 Variables, 4 Observations - UNF:6:yq7KQEdVC0k1T86KGkSn0g== Overall evaluation of the custom-trained model restricted to the standard spaCy entity types (PER, LOC and ORG). This output enables direct comparison with the off-the-shelf spaCy models presented in the article.
navez_spacy_custom_trained_evalpertype-2.csv Aug 25, 2026 - Replication Data for: From nineteenth-century letters to entities: "a NER pipeline for French correspondence and its methodological lessons" - Article for Digital Humanities Benelux Journal Comma Separated Values - 2.0 KB - MD5: d770abff6f7b4ac2791c99f080b2ccc9 Detailed evaluation metrics for each entity type recognised by the custom-trained model, including both standard and domain-specific categories (PER, LOC, ORG, GRP, ART, EXH and LETT).
navez_spacy_custom_trained_mismatches.csv Aug 25, 2026 - Replication Data for: From nineteenth-century letters to entities: "a NER pipeline for French correspondence and its methodological lessons" - Article for Digital Humanities Benelux Journal Comma Separated Values - 1.6 MB - MD5: bd7431776ef54f320a6345ee2c39b5d0 Token-level comparison between predicted and gold-standard IOB labels for the custom-trained spaCy model. Used for the qualitative error analysis discussed in the article.
navez_spacy_custom_trained_results.csv Aug 25, 2026 - Replication Data for: From nineteenth-century letters to entities: "a NER pipeline for French correspondence and its methodological lessons" - Article for Digital Humanities Benelux Journal Comma Separated Values - 155.9 KB - MD5: 519958789ccf7a67f90669ce21103d90 Predictions generated by the custom-trained fr_core_news_lg model after fine-tuning on the Navez gold-standard corpus. Includes all project-specific entity types (PER, LOC, ORG, GRP, ART, EXH and LETT).
navez_spacy_off_the_shelf_ner_lg_evalall-2.csv Aug 25, 2026 - Replication Data for: From nineteenth-century letters to entities: "a NER pipeline for French correspondence and its methodological lessons" - Article for Digital Humanities Benelux Journal Comma Separated Values - 410 B - MD5: 27ce89c83902be5851a3c2a3a4c0cf30 Overall evaluation results for the off-the-shelf fr_core_news_lg model. Reports precision, recall and F1 scores under the Strict, Exact, Partial and Type evaluation scenarios using the Nervaluate framework.

length_summary.tab

Aug 25, 2026 - Replication Data for: From nineteenth-century letters to entities: "a NER pipeline for French correspondence and its methodological lessons" - Article for Digital Humanities Benelux Journal

Tabular Data - 533 B - 5 Variables, 9 Observations -

Summary statistics describing the distribution of document subword lengths in the evaluation corpus splitsand their relationship to model performance. Used to assess the number of letters affected by preprocessing.

navez_gs_preprocessed-2.csv

Comma Separated Values - 1015.3 KB -

Preprocessed version of the manually annotated corpus after cleaning and conversion from Label Studio. Contains token- and entity-level information used for model training and evaluation.

navez_gs_preprocessed-2.pkl

Unknown - 33.0 MB -

Python pickle version of the preprocessed gold-standard corpus, preserving data structures used directly in the notebooks.

Navez_ner_finetuning_weightedcrossentropy.ipynb

Jupyter Notebook - 4.6 MB -

Notebook for fine-tuning and evaluating French transformer-based models for Named Entity Recognition on the Navez correspondence. It implements the experiments with CamemBERT, CamemBERTav2, D'AlemBERT and Europeana BERT, including weighted cross-entropy training, hyperparameter o...

navez_spacy_custom_trained_evalall-2.csv

Comma Separated Values - 424 B -

Overall evaluation metrics for the custom-trained spaCy model, including the four project-specific entity types introduced during fine-tuning. Reports precision, recall and F1 under the Nervaluate evaluation scenarios.

navez_spacy_custom_trained_evalall_no_dk-2.tab

Tabular Data - 462 B - 1 Variables, 4 Observations -

Overall evaluation of the custom-trained model restricted to the standard spaCy entity types (PER, LOC and ORG). This output enables direct comparison with the off-the-shelf spaCy models presented in the article.

navez_spacy_custom_trained_evalpertype-2.csv

Comma Separated Values - 2.0 KB -

Detailed evaluation metrics for each entity type recognised by the custom-trained model, including both standard and domain-specific categories (PER, LOC, ORG, GRP, ART, EXH and LETT).

navez_spacy_custom_trained_mismatches.csv

Comma Separated Values - 1.6 MB -

Token-level comparison between predicted and gold-standard IOB labels for the custom-trained spaCy model. Used for the qualitative error analysis discussed in the article.

navez_spacy_custom_trained_results.csv

Comma Separated Values - 155.9 KB -

Predictions generated by the custom-trained fr_core_news_lg model after fine-tuning on the Navez gold-standard corpus. Includes all project-specific entity types (PER, LOC, ORG, GRP, ART, EXH and LETT).

navez_spacy_off_the_shelf_ner_lg_evalall-2.csv

Comma Separated Values - 410 B -

Overall evaluation results for the off-the-shelf fr_core_news_lg model. Reports precision, recall and F1 scores under the Strict, Exact, Partial and Type evaluation scenarios using the Nervaluate framework.

Add Data

Share Dataverse

Link Dataverse

Reset Modifications