--- tags: - setfit - sentence-transformers - text-classification - generated_from_setfit_trainer widget: - text: Etunimi Etunimi menetkö noin vaan takuuseen, ettei sodan johdosta näin käy? Ite en kyllä menis 100% sanomaan mitään mihin liittyy Putin ja Putinin sota - text: Kohta on lisää lapsia sairaalassa koronan vuoksi ☹ - text: Etunimi Sukunimi pyöräily sekä kävely ovat hyvää liikuntaa - text: Etunimi Sukunimi Niin.. Nuo todelliset tartunyamäärät voivat olla ihan mitä tahansa. Mihinkään rajoitustoimiin ei tarvitsisi ryhtyä. Ihmiset voivat itse pitää huolta itsestää, ja valtion tehtävä on pitää huolta siitä että hoitokapasiteetti riittää. Tällä hetkellä meillä ei ole mitään hätää. Koko Suomessa tehohoidossa koronan vuoksi on noin 2p ihmistä. Tehohoitopaikkoja siis riittää vielä vaikka ja kuinka jos tarvetta. Korostan, että edelleenkin ovat turvavälit, hyvä hygienia ja turhien kontaktien välttäminen kaikkein tärkeintä. Mitään ei tarvitsisi rajoittaa, jollei ihmiset olisi niin helvetin tyhmiä, että osaisivat ajatella ihan omilla aivoillaan, eikä valtion tarvitsisi heitä opastaa kädestä pitäen kuten jotain pieniä lapsia. - text: Etunimi hallituksella pitää kuitenkin olla jokin pohja johon perustavat päätöksensä. Poikkeustilaa ei voi loputtomiin jatkaa vain mutulla, jolloin heidän on kuunneltava aiheen ammattilaisia. metrics: - metric pipeline_tag: text-classification library_name: setfit inference: true base_model: TurkuNLP/bert-base-finnish-cased-v1 model-index: - name: SetFit with TurkuNLP/bert-base-finnish-cased-v1 results: - task: type: text-classification name: Text Classification dataset: name: Unknown type: unknown split: test metrics: - type: metric value: 0.8718523964493842 name: Metric --- # Detect Actions in Asynchronous Conversation Comments ## SetFit with TurkuNLP/bert-base-finnish-cased-v1 This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification of actions in asynchronous conversation. This particular model detects if a comment includes a statement or not. The configuration of the model is that the model is based on averaged annotations (from 3 annotators). Metric evaluations are based on conservative ground truth (see paper). This SetFit model uses TurkuNLP/bert-base-finnish-cased-v1 as the Sentence Transformer embedding model (using word embeddings). A LogisticRegression instance is used for classification. The model has been trained using an efficient few-shot learning technique that involves: 1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning. 2. Training a classification head with features from the fine-tuned Sentence Transformer. ## Model Details ### Model Description - **Model Type:** SetFit - **Sentence Transformer body:** [TurkuNLP/bert-base-finnish-cased-v1](https://huggingface.co/TurkuNLP/bert-base-finnish-cased-v1) - **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance - **Maximum Sequence Length:** 512 tokens - **Number of Classes:** 2 classes (action present yes/no) ### Model Sources - **Repository:** [GitHub](https://github.com/henniina/Detecting-paired-actions) - **Paper:** Paakki, H., Toivanen, P. and Kajava K. (2025). Implicit and Indirect: Detecting Face-threatening and Paired Actions in Asynchronous Online Conversations. Northern European Journal of Language Technology (NEJLT), 11(1), pp. 58-83. - ### Model Labels | Label | Examples | |:------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | 0 | | | 1 | | ## Evaluation ### Metrics | Label | Metric | |:--------|:-------| | **5-fold cross-validated F1** | 0.74 | ## Uses ### Direct Use for Inference First install the SetFit library: ```bash pip install setfit ``` Then you can load this model and run inference. ```python from setfit import SetFitModel # Download from the 🤗 Hub model = SetFitModel.from_pretrained("Finnish-actions/SetFit-FinBERT1-Avg-statement") # Run inference preds = model("Kohta on lisää lapsia sairaalassa koronan vuoksi ☹") ``` ### Downstream Use NB. This model has been trained on data coming from Finnish language asynchronous conversations under crisis related news on Facebook. This specific model has been trained to detect whether a comment includes a question or not. It reflects only one of our annotators' label interpretations, so the best use of our models (see our paper) would be to combine a set of models we provide on our Huggingface (Finnish-actions), and use a model ensemble to provide label predictions. It needs to be noted also that the model may not be well applicable outside of its empirical context, so in downstream applications, one should always conduct an evaluation of the model applicability using manually annotated data from that specific context (see our paper for annotation instructions). ## Out-of-Scope Use Please use this model only for action detection and analysis. Uses of this model and the involved data for generative purposes (e.g. NLG) is prohibited. ### Bias, Risks and Limitations Note that the model may produce errors. Due to the size of the training dataset, model may not generalize very well even for other novel topics within the same context. Note that model predictions should not be regarded as final judgments e.g. for online moderation purposes, but each case should also be regarded individually if using model predictions to support moderation. Also, the annotations only reflect three (though experienced) annotators' interpretations, so there might be perspectives on data intepretation that have not been taken into account here. If model is used to support moderation on social media, we recommend that final judgments should always be left for human moderators. ## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:-------------|:----|:--------|:----| | Word count | 1 | 19.9323 | 213 | | Label | Training Sample Count | |:------|:----------------------| | 0 | 218 | | 1 | 624 | ### Framework Versions - Python: 3.11.9 - SetFit: 1.1.3 - Sentence Transformers: 3.2.0 - Transformers: 4.44.0 - PyTorch: 2.4.0+cu124 - Datasets: 2.21.0 - Tokenizers: 0.19.1 ## Citation ### BibTeX ```bibtex @article{paakki-implicit-indirect, doi = {https://doi.org/10.3384/nejlt.2000-1533.2025.5980}, url = {https://nejlt.ep.liu.se/article/view/5980}, author = {Paakki, Henna and Toivanen, Pihla and Kajava, Kaisla}, title = {Implicit and Indirect: Detecting Face-threatening and Paired Actions in Asynchronous Online Conversations}, publisher = {Northern European Journal of Language Technology (NEJLT)}, volume= {11}, number= {1}, year = {2025} } ```