diff --git a/README.md b/README.md
index beb6d0c4..7b36bed7 100644
--- a/README.md
+++ b/README.md
@@ -98,6 +98,7 @@ For more tasks, datasets and results in Chinese, check out the [Chinese NLP](htt
 
 ### Bengali
 - [Part-of-speech Tagging](bengali/part_of_speech_tagging.md)
+- [Emotion Detection](bengali/emotion_detection.md)
 - [Sentiment Analysis](bengali/sentiment_analysis.md)
 
 ### Persian
diff --git a/bengali/emotion_detection.md b/bengali/emotion_detection.md
new file mode 100644
index 00000000..808107da
--- /dev/null
+++ b/bengali/emotion_detection.md
@@ -0,0 +1,11 @@
+# Fine-grained Emotion Detection
+
+Fine-grained Emotion Detection is the task of detecting one or multiple emotion of a given text.
+
+## EmoNoBa
+
+[EmoNoBa: A Dataset for Analyzing Fine-Grained Emotions on Noisy Bangla Texts](https://aclanthology.org/2022.aacl-short.17.pdf) is a dataset which contains 22,698 instances with each labeled with one or atmost all 6 emotions. The dataset is available [here](https://www.kaggle.com/datasets/saifsust/emonoba). The models are evaluated based on Macro Average F1-score.
+
+| Model | F1-score | Paper / Source | Code |
+| ------------ | ------------- | ------------ | ------------- |
+| W1 + W2 + W3+ W4 + C1 + C2 + C3 | 42.81 | [EmoNoBa: A Dataset for Analyzing Fine-Grained Emotions on Noisy Bangla Texts](https://aclanthology.org/2022.aacl-short.17.pdf) | [Official](https://github.com/KhondokerIslam/EmoNoBa) |