Davlan/naija-twitter-sentiment-afriberta-large

Nigerian Pidgin(pcm)Sentiment Classification (AfriBERTa fine-tune)castorini/afriberta_largeXLMRobertaForSequenceClassification

View Source

Model Info

Language

Nigerian Pidgin (pcm)

Architecture

XLMRobertaForSequenceClassification

Institution

Adelani, David et al. (Davlan / Masakhane)

Last Updated

11 Jun 2026

Intended Use Cases

Sentiment (pcm + hau + ibo + yor)

License & Access

SPDX identifierCC-BY-4.0

Open — attribution required; commercial use allowed.

Provenance

Source URL

https://huggingface.co/Davlan/naija-twitter-sentiment-afriberta-large

Fetch Timestamp

11 Jun 2026

Submitter

Adelani, David et al. (Davlan / Masakhane)

Full Record

20 of 25 fields stated

Every column the registry tracks. Values marked derivedwere filled by a rule or read from the source's text rather than stated in its metadata; the rule or the quoted sentence is shown under the value.

Registry columns (17/18)

iso code: pcm
Model Name: Davlan/naija-twitter-sentiment-afriberta-large
Where is it hosted: HuggingFace
Link: https://huggingface.co/Davlan/naija-twitter-sentiment-afriberta-large
Year: 2022
Creator/Author(s): Adelani, David et al. (Davlan / Masakhane)
Paper Reference: Muhammad et al. (2022). NaijaSenti. LREC 2022.
NLP Task: Sentiment Classification (AfriBERTa fine-tune)
Architecture: XLMRobertaForSequenceClassificationderivedHugging Face config: architectures / model_type
Base Model: castorini/afriberta_large
Fine-tuned?: Yes
License: CC-BY-4.0
Open Access: Open
Has Model Card: Yes
SOTA Tasks: Sentiment (pcm + hau + ibo + yor)
Verified By: Not stated
Date Indexed: 2026-06-11
Comment: Multilingual sentiment model fine-tuned on NaijaSenti for Nigerian Pidgin and 3 other Nigerian languages. SOTA on NaijaSenti benchmark at time of publication.

Readiness (LRS) (3/7)

model id: davlan-naija-twitter-sentiment-afriberta-large-pcm
Model Type: OtherderivedHugging Face card: pipeline_tag
Training Data Sources: NaijaSenti corpus (Hausa, Igbo, Nigerian Pidgin, Yoruba)
Benchmark Used: Not stated
Benchmark Score: Not stated
Benchmark Date: Not stated
Status: Not stated