We are pleased to announce the publication of a supplement in Biomedical Informatics Insights on finding emotions in suicide notes with machine learning tools.  To learn more about the origins of the supplement read the summary article: 'Sentiment Analysis of Suicide Notes: A Shared Task'

The supplement includes the following papers:

• A Combined Approach to Emotion Detection in Suicide Notes

• A Hybrid Approach to Sentiment Sentence Classification in Suicide Notes

• A Hybrid Model for Automatic Emotion Recognition in Suicide Notes

• A Hybrid system for Emotion Extraction from Suicide Notes

• A Naïve Bayes Approach to Classifying Topics in Suicide Notes

• Binary Classifiers and Latent Sequence Models for Emotion Detection in Suicide Notes

• Combining Lexico-semantic Features for Emotion Classification in Suicide Notes

• Discovering Fine-grained Sentiment in Suicide Notes

• Early fusion of low level features for emotion mining

• Emotion Detection in Suicide Notes using Maximum Entropy Classification

• Fine-grained emotion detection in suicide notes: A thresholding approach to multi-label classification

• Labeling Emotions in Suicide Notes: Cost-Sensitive Learning with Heterogeneous Features

• LASSA: Emotion Detection via Information Fusion

• Leveraging Psycholinguistic Resources and Emotional Sequence Models for Suicide Note Emotion Annotation

• Rule-based and Lightly Supervised Methods to Predict Emotions in Suicide Notes

• Sentiment Analysis of Suicide Notes: A Shared Task

• Statistical and similarity methods for classifying emotion in suicide notes

• Suicide Note Sentiment Classification: A Supervised Approach Augmented by Web Data

• Three hybrid classifiers for the detection of emotions in suicide notes

• Topic Categorisation of Statements in Suicide Notes with Integrated Rules and Machine Learning

• Using Ensemble Models to Classify the Sentiment Expressed in Suicide Notes