000210030 001__ 210030
000210030 005__ 20181001181640.0
000210030 037__ $$aCONF
000210030 245__ $$aExplaining the Stars: Weighted Multiple-Instance Learning for Aspect-Based Sentiment Analysis
000210030 269__ $$a2014
000210030 260__ $$c2014
000210030 336__ $$aConference Papers
000210030 520__ $$aThis paper introduces a model of multiple-instance learning applied to the prediction of aspect ratings or judgments of specific properties of an item from user-contributed texts such as product reviews. Each variable-length text is represented by several independent feature vectors; one word vector per sentence or paragraph.  For learning from texts with known aspect ratings, the model performs multiple-instance regression (MIR) and assigns importance weights to each of the sentences or paragraphs of a text, uncovering their contribution to the aspect ratings. Next, the model is used to predict aspect ratings in previously unseen texts, demonstrating interpretability and explanatory power for its predictions.  We evaluate the model on seven multi-aspect sentiment analysis data sets, improving over four MIR baselines and two strong bag-of-words  linear models, namely SVR and Lasso, by more than 10% relative in terms of MSE.
000210030 6531_ $$aaspect-based sentiment analysis
000210030 6531_ $$aMultiple-Instance Learning
000210030 6531_ $$aSentiment Analysis
000210030 700__ $$0247398$$aPappas, Nikolaos$$g221791
000210030 700__ $$aPopescu-Belis, Andrei
000210030 7112_ $$aConference on Empirical Methods in Natural Language Processing$$cDoha, Qatar
000210030 8564_ $$s922262$$uhttps://infoscience.epfl.ch/record/210030/files/Pappas_EMNLP_2014.pdf$$yn/a$$zn/a
000210030 909C0 $$0252189$$pLIDIAP$$xU10381
000210030 909CO $$ooai:infoscience.tind.io:210030$$pconf$$pSTI$$qGLOBAL_SET
000210030 937__ $$aEPFL-CONF-210030
000210030 970__ $$aPappas_EMNLP_2014/LIDIAP
000210030 980__ $$aCONF