Downloads · 30 days
50
37% of all-time downloads
ZhiyangQi97/japanese-x-ragebait-line-distilbert-base
japanese-x-ragebait-line-distilbert-base is a text classification model from ZhiyangQi97. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as apache-2.0.
This is the LINE DistilBERT component of the three-model ragebait detector from “From Detection to Characterization: A Large-Scale Study of Ragebait on Japanese X” (WI-IAT 2026). It is a binary Japanese text classifie…
Downloads · 30 days
50
37% of all-time downloads
All-time downloads
136
Public
Parameters
68.7M
275 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors275 MB · 100%
From the Hugging Face model README
This is the LINE DistilBERT component of the three-model ragebait detector from “From Detection to Characterization: A Large-Scale Study of Ragebait on Japanese X” (WI-IAT 2026). It is a binary Japanese text classifier fine-tuned from line-corporation/line-distilbert-base-japanese.
NO (0): non-ragebaitYES (1): ragebaitThe labels are research annotations and should not be treated as facts about a post or its author.
YES and NOYES and NO2e-5The public dataset repository contains only Post IDs and labels, not redistributed post text: ZhiyangQi/japanese-x-ragebait.
| Metric | Value |
|---|---|
| Accuracy | 82.65% |
Precision (YES) | 81.79% |
Recall (YES) | 84.00% |
| Macro-F1 | 82.65% |
The confusion matrix is [[813, 187], [160, 840]], ordered as NO, YES. Full training history and unrounded values are in training_results.json.
import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer
model_id = "ZhiyangQi97/japanese-x-ragebait-line-distilbert-base"
tokenizer = AutoTokenizer.from_pretrained(
model_id,
use_fast=False,
trust_remote_code=True,
)
model = AutoModelForSequenceClassification.from_pretrained(model_id)
text = "分類したい日本語テキスト"
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=256)
with torch.inference_mode():
prediction = model(**inputs).logits.argmax(dim=-1).item()
print(model.config.id2label[prediction])
Install transformers, torch, sentencepiece, fugashi, and unidic-lite before loading the tokenizer. Review the included custom tokenizer code before enabling trust_remote_code=True.
This model is intended for non-commercial academic research on Japanese ragebait. The training labels were created with an LLM-assisted pipeline and may contain errors. Ragebait is contextual and intent-based; performance may degrade on other periods, platforms, languages, or domains. Do not use this model to profile, rank, target, identify, harass, moderate, or make consequential decisions about individual users.
The base model is distributed under the Apache License 2.0. See the base model card for its terms and documentation.
@inproceedings{qi2026ragebait,
title = {From Detection to Characterization: A Large-Scale Study of Ragebait on Japanese X},
author = {Qi, Zhiyang and Ito, Kazuhiro and Chen, Jinghui and Nakamura, Hibiki and Chen, Zhangxuan and Murata, Erina and Chujyo, Masaki and Toriumi, Fujio},
booktitle = {WI-IAT 2026},
year = {2026}
}