Polarity and Intensity: the Two Aspects of Sentiment Analysis

Current multimodal sentiment analysis frames sentiment score prediction as a general Machine Learning task. However, what the sentiment score actually represents has often been overlooked. As a measurement of opinions and affective states, a sentiment score generally consists of two aspects: polarity and intensity. We decompose sentiment scores into these two aspects and study how they are conveyed through individual modalities and combined multimodal models in a naturalistic monologue setting. In particular, we build unimodal and multimodal multi-task learning models with sentiment score prediction as the main task and polarity and/or intensity classification as the auxiliary tasks. Our experiments show that sentiment analysis benefits from multi-task learning, and individual modalities differ when conveying the polarity and intensity aspects of sentiment.

[1]  Christopher Potts,et al.  Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank , 2013, EMNLP.

[2]  Johanna D. Moore,et al.  Twitter Sentiment Analysis: The Good the Bad and the OMG! , 2011, ICWSM.

[3]  Qiang Yang,et al.  An Overview of Multi-task Learning , 2018 .

[4]  Erik Cambria,et al.  Multi-attention Recurrent Network for Human Communication Comprehension , 2018, AAAI.

[5]  Hatice Gunes,et al.  Continuous Prediction of Spontaneous Affect from Multiple Cues and Modalities in Valence-Arousal Space , 2011, IEEE Transactions on Affective Computing.

[6]  Louis-Philippe Morency,et al.  Multimodal Sentiment Intensity Analysis in Videos: Facial Gestures and Verbal Messages , 2016, IEEE Intelligent Systems.

[7]  Andrew Ortony,et al.  The Cognitive Structure of Emotions , 1988 .

[8]  Erik Cambria,et al.  Tensor Fusion Network for Multimodal Sentiment Analysis , 2017, EMNLP.

[9]  Benoit Huet,et al.  Bimodal Emotion Recognition , 2010, ICSR.

[10]  Sebastian Ruder,et al.  An Overview of Multi-Task Learning in Deep Neural Networks , 2017, ArXiv.

[11]  P. Ekman.  An argument for basic emotions , 1992 .

[12]  Erik Cambria,et al.  Deep Convolutional Neural Network Textual Features and Multiple Kernel Learning for Utterance-level Multimodal Sentiment Analysis , 2015, EMNLP.

[13]  Yang Liu,et al.  A Multi-Task Learning Framework for Emotion Recognition Using 2D Continuous Space , 2017, IEEE Transactions on Affective Computing.

[14]  Erkki Sutinen,et al.  Are They Different? Affect, Feeling, Emotion, Sentiment, and Opinion Detection in Text , 2014, IEEE Transactions on Affective Computing.

[15]  Bruno Pouliquen,et al.  Sentiment Analysis in the News , 2010, LREC.

[16]  Erik Cambria,et al.  Context-Dependent Sentiment Analysis in User-Generated Videos , 2017, ACL.

[17]  Tao Chen,et al.  Improving sentiment analysis via sentence type classification using BiLSTM-CRF and CNN , 2017, Expert Syst. Appl..

[18]  Theresa Wilson.  Fine-grained subjectivity and sentiment analysis: recognizing the intensity, polarity, and attitudes of private states , 2008 .

[19]  Johanna D. Moore,et al.  Recognizing emotions in spoken dialogue with hierarchically fused acoustic and lexical features , 2016, 2016 IEEE Spoken Language Technology Workshop (SLT).

[20]  Erik Cambria,et al.  Multimodal Language Analysis in the Wild: CMU-MOSEI Dataset and Interpretable Dynamic Fusion Graph , 2018, ACL.

[21]  J. Russell.  A circumplex model of affect. , 1980 .

[22]  Louis-Philippe Morency,et al.  Multimodal Machine Learning: A Survey and Taxonomy , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.