First published: 2017/11/27 (4 years ago) Abstract: We consider the task of fine-grained sentiment analysis from the perspective
of multiple instance learning (MIL). Our neural model is trained on document
sentiment labels, and learns to predict the sentiment of text segments, i.e.
sentences or elementary discourse units (EDUs), without segment-level
supervision. We introduce an attention-based polarity scoring method for
identifying positive and negative text snippets and a new dataset which we call
SPOT (as shorthand for Segment-level POlariTy annotations) for evaluating
MIL-style sentiment models like ours. Experimental results demonstrate superior
performance against multiple baselines, whereas a judgement elicitation study
shows that EDU-level opinion extraction produces more informative summaries
than sentence-based alternatives.