Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · avichr

heBERT_sentiment_analysis

heBERT_sentiment_analysis is a BERT-family text-classification model from avichr. According to the model card, it builds on HeBERT, a Hebrew BERT-Base model for polarity analysis and emotion recognition.

Publisher
avichr
Task
text-classification
Model type
bert
License
Unknown
Library
transformers
Publication status
Approved for indexing

Model overview

heBERT_sentiment_analysis is published by avichr as a text-classification model. The captured configuration identifies BertForSequenceClassification with model type bert. According to the model card, it builds on HeBERT, a Hebrew pre-trained BERT-Base model evaluated for sentiment analysis and emotion recognition.

Recorded capabilities

Hebrew BERT-Base foundation

According to the model card, HeBERT is a Hebrew pre-trained language model based on Google's BERT architecture in BERT-Base configuration.

Three-source Hebrew pretraining

According to the model card, pretraining used Hebrew OSCAR with about 1 billion words, Hebrew Wikipedia with over 63 million words, and Emotion UGC with over 7 million words.

Emotion and polarity annotation

According to the model card, crowd members annotated 4,000 sentences for anger, disgust, expectation, fear, happy, sadness, surprise, trust, and overall sentiment.

Use cases in the source record

  • Hebrew sentiment and polarity analysis workflows covered by the card's downstream evaluation description.
  • Hebrew emotion-recognition experiments using the card's eight-emotion annotation scheme.

Limitations and unknowns

  • No parameter count was extracted from this record.
  • No license value was extracted from this record.
  • No context-window value was extracted from this record.
  • No evaluation results were extracted from this record.
  • Provider state is historical snapshot data, not independently refreshed current availability.
  • Pretraining and annotation details are publisher claims and were not independently verified.

Source and provenance

Source: avichr/heBERT_sentiment_analysis

Captured: Unknown. Processed: 2026-09-07T19:34:40.457402+00:00.

HeBERT: Pre-trained BERT for Polarity Analysis and Emotion Recognition HeBERT is a Hebrew pre-trained language model. It is based on Google's BERT architecture and it is BERT-Base config (Devlin et al. 2018) . HeBert was trained on three datasets: A Hebrew version of OSCAR (Ortiz, 2019) : ~9.8 GB of data, including 1 billion words and over 20.8 million sentences. A Hebrew dump of Wikipedia: ~650 MB of data, including over 63 million words and 3.8 million sentences Emotion UGC data was collected for the purpose of this study. (described below) We evaluated the model on emotion recognition and sentiment analysis, for downstream tasks.…

F001F002F003F004F005F006F008F009F010F011F012F013F014