Sentiment Analysis in the Medical Domain

 8.2.3 Intensity classification. .-  8.2.4 Emotion recognition..-  9 Document pre-processing.-  9.1 Overview.-  9.2 Data collection and preparation.-  9.3 Text normalisation. .-  9.4 Feature extraction. .-  9.4.1 Bag of words.-  9.4.2 Distributed representation.-  9.5 Feature selection. . .-  9.6 Topic detection..-  Contents xi .-  Lexicon-based medical sentiment analysis..-  1 Overview on lexicon-based approaches..- 2 Approaches to lexicon generation.-  achine learning-based sentiment analysis approaches.- .1 Unsupervised learning approaches . .- .1.1 Partition methods.-  1.2 Hierarchical clustering methods..-  1.2 Supervised approaches .-  .2.1 Linear approaches .-  .2.2 Probabilistic approaches. .- 2.3 Rule-based classifier.- .2.4 Decision tree classifier. .- .3 Semi-supervised approaches. . .- .4 Deep learning approaches .- .4.1 Deep neural networks (DNN).-  .4.2 Convolutional neural networks (CNN).-  .4.3 Long short-term memory (LSTM)..-  11.5 Hybrid approaches.- 11.6 Concluding remarks.-  12 Sentiment analysis tools.- 12.1 Sentiment: Sentiment Analysis Tool..- 12.2 TextBlob.- 12.3 Pattern for Python..- 12.4 Valence Aware Dictionary and Sentiment Reasoner (VADER).- 12.5 TensiStrength.- 12.6 LIWC83.- 12.7 Other tools.-  13 Case studies.- 13.1 Learning about suicidal ideation.- 13.1.1 The problem.- 13.1.2 Solution overview.- 13.1.3 Methods and procedures.- 13.2 Predicting the psychiatric readmission risk.- 13.2.1 The problem.- 13.2.2 Solution overview.- 13.2.3 Methods and procedures.- .13.3 Generating a corpus for clinical sentiment analysis.- 13.3.1 The problem.- 13.3.2 Solution overview.- 13.3.3 Methods and procedures. .-  13.4 Conversational agent with emotion recognition.- 13.4.1 The problem.- xii Contents.-  13.4.2 Solution overview.-  13.4.3 Methods and procedures. .-  13.5 Surveillance of public opinions in times of pandemics .-  13.5.1 The problem.-  13.5.2 Solution overview.-  13.5.3 Methods and procedures. .-  13.6 Providing quality information about hospitals.-  13.6.1 The problem.-  13.6.2 Solution overview.-  13.6.3 Methods and procedures. .-  Part IV Future.- 14 Medical sentiment analysis - Quo vadis?.- 14.1 SWOT strategy..-  14.2 Strengths.-  14.3 Weaknesses..-  14.4 Opportunities.-  14.5 Threats101 15 Open challenges related to language. .-  15.1 Specific language phenomena hampering sentiment analysis. . .-  15.1.1 Negations .-  15.1.2 Valence shifters .-  15.1.3 Paraphrasing, sarcasm and irony..-  15.1.4 Comparative sentences. .-  15.1.5 Coordination structures.-  15.1.6 Word ambiguity..-  15.2 Evolution of language.-  16 Responsible sentiment analysis in healthcare..-  16.1 Ethical principles applied to medical sentiment analysis.-  16.2 Respect for autonomy.-  16.3 Beneficience and non-maleficience .-  16.4 Justice.-  16.5 Explicability and trust.-  16.6 Concluding remarks.-  17 Explainable sentiment analysis..-  17.1 Definition and need for XAI. . .-  17.2 Explainable AI methods.-  17.3 Applications of XAI to medical sentiment analysis.-  Contents xiii 18 The future of medical sentiment analysis.-  18.1 Current research gaps in medical sentiment analysis.-  18.2 Towards domain-specific resources: Lexicons and datasets..-  18.3 Addressing domain-specific challenges and increasing accuracy. .-  18.4 Towards understandable and ethical sentiment analysis..-  18.5 Demonstrate the benefit for patient care..-  18.6 Concluding remarks.-  References.-  Glossary..-  Index.