---
title: "Context-Dependent Sentiment Analysis in — Poria 2017"
description: "Most multimodal sentiment systems for video label each utterance as if it stood alone and ignore what the speaker said just before and after."
authors: ["Soujanya Poria", "Erik Cambria", "Devamanyu Hazarika", "Navonil Majumder", "Amir Zadeh", "Louis-Philippe Morency"]
year: 2017
venue: "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/P17-1081/"
doi: "10.18653/v1/p17-1081"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/poria-2017-context-dependent-sentiment-analysis-user/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/poria-2017-context-dependent-sentiment-analysis-user/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2017](https://md.research.elamur.ai/free/en/papers/2017/) / Context-Dependent Sentiment Analysis in User-Generated Videos

# Context-Dependent Sentiment Analysis in User-Generated Videos

**Authors:** [Soujanya Poria](https://md.research.elamur.ai/free/en/authors/soujanya-poria/), [Erik Cambria](https://md.research.elamur.ai/free/en/authors/erik-cambria/), [Devamanyu Hazarika](https://md.research.elamur.ai/free/en/authors/devamanyu-hazarika/), [Navonil Majumder](https://md.research.elamur.ai/free/en/authors/navonil-majumder/), [Amir Zadeh](https://md.research.elamur.ai/free/en/authors/amir-zadeh/), [Louis-Philippe Morency](https://md.research.elamur.ai/free/en/authors/louis-philippe-morency/) · **Institutions:** [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) · [National University of Singapore](https://md.research.elamur.ai/free/en/universities/national-university-of-singapore/) · [Nanyang Technological University](https://md.research.elamur.ai/free/en/universities/nanyang-technological-university/) · [Instituto Politécnico Nacional](https://md.research.elamur.ai/free/en/universities/instituto-politecnico-nacional/) · [Temasek Laboratories@NTU](https://md.research.elamur.ai/free/en/labs/temasek-laboratories-ntu/) · National Institute of Technology Warangal · **Year:** 2017 · **Venue:** Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/P17-1081/) · [PDF](https://aclanthology.org/P17-1081.pdf) · [DOI 10.18653/v1/p17-1081](https://doi.org/10.18653/v1/p17-1081) · [OpenAlex](https://openalex.org/W2740550900)

**Citations:** 894 citations (OpenAlex, 2026-10-14) · [125](https://md.research.elamur.ai/free/en/papers/poria-2017-context-dependent-sentiment-analysis-user/cited-by/) in our library, of the 140884 papers whose bibliographies we read

## Summary
Most multimodal sentiment systems for video label each utterance as if it stood alone and ignore what the speaker said just before and after. Poria et al. argue that neighbouring utterances in a video are often correlated in sentiment, so the surrounding context should inform each prediction. Their pipeline has two stages. First, each utterance is encoded separately for each modality: text with a CNN over word2vec embeddings, audio with openSMILE descriptors, and visual input with a 3D-CNN. Second, the per-utterance vectors of a whole video are passed as a sequence through a contextual LSTM. The LSTM produces context-aware features that feed unimodal classifiers and a hierarchical multimodal fusion. The authors test several LSTM variants against an SVM baseline on MOSI (English reviews), MOUD (Spanish reviews) and IEMOCAP (emotions). They report gains of roughly 5–10% over earlier state-of-the-art results. They also examine how much each modality contributes and how well models transfer across datasets and languages, issues that previous work had largely left aside.

## Key points
- **Data:** MOSI and MOUD are used for sentiment polarity. IEMOCAP is used for four emotion classes: angry, happy, sad and neutral.
- **Unimodal features:**
  - Text: a two-layer text-CNN over 300-dimensional Google News word2vec vectors, with each utterance padded or cut to 50 words.
  - Audio: openSMILE with the IS13-ComParE configuration, giving 6373 features.
  - Visual: a 3D-CNN that captures change across consecutive frames.
- **Main results:**
  - Trimodal (T+V+A) accuracy with hierarchical fusion is 80.30% on MOSI and 68.11% on MOUD.
  - The previously reported best results cited were 73.55% and 63.25%.
- **Model comparison:** Compared variants are uni-SVM, h-LSTM, sc-LSTM and bc-LSTM. Bimodal and trimodal setups consistently beat unimodal ones, and audio is generally stronger than visual.
- **Cross-dataset test:** Training on MOSI and testing on MOUD (English to Spanish) gives low accuracy, at most about 52.7%. In this setting the visual modality transfers better than text or audio.

## Interesting ideas
- **Treat a document as a sequence of independently encoded units.** Each segment (here an utterance) is first encoded on its own, then a recurrent layer runs over the segment vectors so every label can draw on nearby segments. The same two-stage pattern could apply to sentence-level sentiment in long reviews or turn-level labels in dialogue transcripts.
- **Keep encoders decoupled from the context model.** Each modality gets its own context-free encoder, and only then is a shared sequence model applied. This makes it easy to swap feature extractors, for example a different language's embeddings, without redesigning the contextual part.
- **Use cross-lingual transfer as a diagnostic.** Training on one language's dataset and testing on another shows which signals are language-independent (facial cues here) and which are language-bound (text and audio). This is a cheap probe when planning resources for a lower-resource language such as Ukrainian.
- **Do error analysis by modality.** The authors trace disagreements between modalities, such as enthusiastic intonation masking a negation that the text model catches. They also note that weak, context-free utterances get pulled toward their neighbours' sentiment. This kind of analysis exposes both the benefit and the main failure mode of context modelling.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

Fields: [Natural language processing](https://md.research.elamur.ai/free/en/shelves/nlp/)

Topics: [Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{poria2017context,
  title = {{Context-Dependent Sentiment Analysis in User-Generated Videos}},
  author = {Poria, Soujanya and Cambria, Erik and Hazarika, Devamanyu and Majumder, Navonil and Zadeh, Amir and Morency, Louis-Philippe},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2017},
  doi = {10.18653/v1/p17-1081},
  url = {https://doi.org/10.18653/v1/p17-1081}
}
```

- [← previous Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://md.research.elamur.ai/free/en/papers/zhao-2017-men-also-like-shopping-reducing/)
- [next → Automated Hate Speech Detection and the Problem of Offensive Language](https://md.research.elamur.ai/free/en/papers/davidson-2017-automated-hate-speech-detection-problem/)
- [↑ back to papers of 2017](https://md.research.elamur.ai/free/en/papers/2017/)

## References

43 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Florian Eyben, Martin Wöllmer, and Björn Schuller. 2010b. Opensmile: the munich versatile and fast open-source audio feature extractor. In Proceedings of the 18th ACM international conference on Multimedia. ACM, pages 1459–1462. [find](https://scholar.google.com/scholar?q=Florian+Eyben%2C+Martin+Wo%CC%88llmer%2C+and+Bjo%CC%88rn+Schuller%2E+2010b%2E+Opensmile%3A+the+munich+versatile+and+fast+open%2Dsource+audio+feature+extractor%2E+In+Proceedings+of+the+18th+ACM+international+conference+on+Mul)
2. Carlos Busso, Murtaza Bulut, Chi-Chun Lee, Abe Kazemzadeh, Emily Mower, Samuel Kim, Jeannette N Chang, Sungbok Lee, and Shrikanth S Narayanan. 2008. Iemocap: Interactive emotional dyadic motion capture database. Language resources and evaluation 42(4):335–359. [find](https://scholar.google.com/scholar?q=Carlos+Busso%2C+Murtaza+Bulut%2C+Chi%2DChun+Lee%2C+Abe+Kazemzadeh%2C+Emily+Mower%2C+Samuel+Kim%2C+Jeannette+N+Chang%2C+Sungbok+Lee%2C+and+Shrikanth+S+Narayanan%2E+2008%2E+Iemocap%3A+Interactive+emotional+dyadic+motion+captur)
3. Felix Gers. 2001. Long Short-Term Memory in Recurrent Neural Networks. Ph.D. thesis, Universität Hannover. [find](https://scholar.google.com/scholar?q=Felix+Gers%2E+2001%2E+Long+Short%2DTerm+Memory+in+Recurrent+Neural+Networks%2E+Ph%2ED%2E+thesis%2C+Universita%CC%88t+Hannover%2E)
4. Erik Cambria, Dipankar Das, Sivaji Bandyopadhyay, and Antonio Feraco. 2017a. A Practical Guide to Sentiment Analysis. Springer, Cham, Switzerland. [find](https://scholar.google.com/scholar?q=Erik+Cambria%2C+Dipankar+Das%2C+Sivaji+Bandyopadhyay%2C+and+Antonio+Feraco%2E+2017a%2E+A+Practical+Guide+to+Sentiment+Analysis%2E+Springer%2C+Cham%2C+Switzerland%2E)
5. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9(8):1735–1780. [find](https://scholar.google.com/scholar?q=Sepp+Hochreiter+and+Ju%CC%88rgen+Schmidhuber%2E+1997%2E+Long+short%2Dterm+memory%2E+Neural+computation+9%288%29%3A1735%E2%80%931780%2E)
6. Erik Cambria, Devamanyu Hazarika, Soujanya Poria, Amir Hussain, and RBV Subramanyam. 2017b. Benchmarking multimodal sentiment aanlysis. In CICLing. [find](https://scholar.google.com/scholar?q=Erik+Cambria%2C+Devamanyu+Hazarika%2C+Soujanya+Poria%2C+Amir+Hussain%2C+and+RBV+Subramanyam%2E+2017b%2E+Benchmarking+multimodal+sentiment+aanlysis%2E+In+CICLing%2E)
7. Shuiwang Ji, Wei Xu, Ming Yang, and Kai Yu. 2013. 3d convolutional neural networks for human action recognition. IEEE transactions on pattern analysis and machine intelligence 35(1):221–231. [find](https://scholar.google.com/scholar?q=Shuiwang+Ji%2C+Wei+Xu%2C+Ming+Yang%2C+and+Kai+Yu%2E+2013%2E+3d+convolutional+neural+networks+for+human+action+recognition%2E+IEEE+transactions+on+pattern+analysis+and+machine+intelligence+35%281%29%3A221%E2%80%93231%2E)
8. Erik Cambria, Soujanya Poria, Rajiv Bajpai, and Björn Schuller. 2016. SenticNet 4: A semantic resource for sentiment analysis based on conceptual primitives. In COLING. pages 2666–2677. [find](https://scholar.google.com/scholar?q=Erik+Cambria%2C+Soujanya+Poria%2C+Rajiv+Bajpai%2C+and+Bjo%CC%88rn+Schuller%2E+2016%2E+SenticNet+4%3A+A+semantic+resource+for+sentiment+analysis+based+on+conceptual+primitives%2E+In+COLING%2E+pages+2666%E2%80%932677%2E)
9. Andrej Karpathy, George Toderici, Sanketh Shetty, Thomas Leung, Rahul Sukthankar, and Li Fei-Fei. 2014. Large-scale video classification with convolutional neural networks. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. pages 1725–1732. [find](https://scholar.google.com/scholar?q=Andrej+Karpathy%2C+George+Toderici%2C+Sanketh+Shetty%2C+Thomas+Leung%2C+Rahul+Sukthankar%2C+and+Li+Fei%2DFei%2E+2014%2E+Large%2Dscale+video+classification+with+convolutional+neural+networks%2E+In+Proceedings+of+the+IEEE+)
10. Erik Cambria and Bebo White. 2014. Jumping NLP curves: A review of natural language processing research. IEEE Computational Intelligence Magazine 9(2):48–57. [find](https://scholar.google.com/scholar?q=Erik+Cambria+and+Bebo+White%2E+2014%2E+Jumping+NLP+curves%3A+A+review+of+natural+language+processing+research%2E+IEEE+Computational+Intelligence+Magazine+9%282%29%3A48%E2%80%9357%2E)
11. Loic Kessous, Ginevra Castellano, and George Caridakis. 2010. Multimodal emotion recognition in speech-based interaction using facial expression, body gesture and acoustic analysis. Journal on Multimodal User Interfaces 3(1-2):33–48. [find](https://scholar.google.com/scholar?q=Loic+Kessous%2C+Ginevra+Castellano%2C+and+George+Caridakis%2E+2010%2E+Multimodal+emotion+recognition+in+speech%2Dbased+interaction+using+facial+expression%2C+body+gesture+and+acoustic+analysis%2E+Journal+on+Multimo)
12. Lawrence S Chen, Thomas S Huang, Tsutomu Miyasato, and Ryohei Nakatsu. 1998. Multimodal human emotion/expression recognition. In Proceedings of the Third IEEE International Conference on Automatic Face and Gesture Recognition. IEEE, pages 366–371. [find](https://scholar.google.com/scholar?q=Lawrence+S+Chen%2C+Thomas+S+Huang%2C+Tsutomu+Miyasato%2C+and+Ryohei+Nakatsu%2E+1998%2E+Multimodal+human+emotion%2Fexpression+recognition%2E+In+Proceedings+of+the+Third+IEEE+International+Conference+on+Automatic+Fac)
13. Yukun Ma, Erik Cambria, and Sa Gao. 2016. Label embedding for zero-shot fine-grained named entity typing. In COLING. Osaka, pages 171–180. [find](https://scholar.google.com/scholar?q=Yukun+Ma%2C+Erik+Cambria%2C+and+Sa+Gao%2E+2016%2E+Label+embedding+for+zero%2Dshot+fine%2Dgrained+named+entity+typing%2E+In+COLING%2E+Osaka%2C+pages+171%E2%80%93180%2E)
14. Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa. 2011. Natural language processing (almost) from scratch. Journal of Machine Learning Research 12(Aug):2493–2537. [find](https://scholar.google.com/scholar?q=Ronan+Collobert%2C+Jason+Weston%2C+Le%CC%81on+Bottou%2C+Michael+Karlen%2C+Koray+Kavukcuoglu%2C+and+Pavel+Kuksa%2E+2011%2E+Natural+language+processing+%28almost%29+from+scratch%2E+Journal+of+Machine+Learning+Research+12%28Aug%29%3A2) [our card](https://md.research.elamur.ai/free/en/papers/collobert-2011-natural-language-processing-almost-scratch/)
15. Navonil Majumder, Soujanya Poria, Alexander Gelbukh, and Erik Cambria. 2017. Deep learning based document modeling for personality detection from text. IEEE Intelligent Systems 32(2):74–79. [find](https://scholar.google.com/scholar?q=Navonil+Majumder%2C+Soujanya+Poria%2C+Alexander+Gelbukh%2C+and+Erik+Cambria%2E+2017%2E+Deep+learning+based+document+modeling+for+personality+detection+from+text%2E+IEEE+Intelligent+Systems+32%282%29%3A74%E2%80%9379%2E)
16. Dragos Datcu and L Rothkrantz. 2008. Semantic audio-visual data fusion for automatic emotion recognition. Euromedia’2008 . [find](https://scholar.google.com/scholar?q=Dragos+Datcu+and+L+Rothkrantz%2E+2008%2E+Semantic+audio%2Dvisual+data+fusion+for+automatic+emotion+recognition%2E+Euromedia%E2%80%992008+%2E)
17. Angeliki Metallinou, Sungbok Lee, and Shrikanth Narayanan. 2008. Audio-visual emotion recognition using gaussian mixture models for face and voice. In Tenth IEEE International Symposium on ISM 2008. IEEE, pages 250–257. [find](https://scholar.google.com/scholar?q=Angeliki+Metallinou%2C+Sungbok+Lee%2C+and+Shrikanth+Narayanan%2E+2008%2E+Audio%2Dvisual+emotion+recognition+using+gaussian+mixture+models+for+face+and+voice%2E+In+Tenth+IEEE+International+Symposium+on+ISM+2008%2E+I)
18. Liyanage C De Silva, Tsutomu Miyasato, and Ryohei Nakatsu. 1997. Facial emotion recognition using multi-modal information. In Proceedings of ICICS. IEEE, volume 1, pages 397–401. [find](https://scholar.google.com/scholar?q=Liyanage+C+De+Silva%2C+Tsutomu+Miyasato%2C+and+Ryohei+Nakatsu%2E+1997%2E+Facial+emotion+recognition+using+multi%2Dmodal+information%2E+In+Proceedings+of+ICICS%2E+IEEE%2C+volume+1%2C+pages+397%E2%80%93401%2E)
19. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 . [find](https://scholar.google.com/scholar?q=Tomas+Mikolov%2C+Kai+Chen%2C+Greg+Corrado%2C+and+Jeffrey+Dean%2E+2013%2E+Efficient+estimation+of+word+representations+in+vector+space%2E+arXiv+preprint+arXiv%3A1301%2E3781+%2E)
20. John Duchi, Elad Hazan, and Yoram Singer. 2011. Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research 12(Jul):2121–2159. [find](https://scholar.google.com/scholar?q=John+Duchi%2C+Elad+Hazan%2C+and+Yoram+Singer%2E+2011%2E+Adaptive+subgradient+methods+for+online+learning+and+stochastic+optimization%2E+Journal+of+Machine+Learning+Research+12%28Jul%29%3A2121%E2%80%932159%2E)
21. David Olson. 1977. From utterance to text: The bias of language in speech and writing. Harvard educational review 47(3):257–281. [find](https://scholar.google.com/scholar?q=David+Olson%2E+1977%2E+From+utterance+to+text%3A+The+bias+of+language+in+speech+and+writing%2E+Harvard+educational+review+47%283%29%3A257%E2%80%93281%2E)
22. Paul Ekman. 1974. Universal facial expressions of emotion. Culture and Personality: Contemporary Readings/Chicago . [find](https://scholar.google.com/scholar?q=Paul+Ekman%2E+1974%2E+Universal+facial+expressions+of+emotion%2E+Culture+and+Personality%3A+Contemporary+Readings%2FChicago+%2E)
23. Luca Oneto, Federica Bisio, Erik Cambria, and Davide Anguita. 2016. Statistical learning theory and ELM for big social data analysis. IEEE Computational Intelligence Magazine 11(3):45–55. [find](https://scholar.google.com/scholar?q=Luca+Oneto%2C+Federica+Bisio%2C+Erik+Cambria%2C+and+Davide+Anguita%2E+2016%2E+Statistical+learning+theory+and+ELM+for+big+social+data+analysis%2E+IEEE+Computational+Intelligence+Magazine+11%283%29%3A45%E2%80%9355%2E)
24. Florian Eyben, Martin Wöllmer, Alex Graves, Björn Schuller, Ellen Douglas-Cowie, and Roddy Cowie. 2010a. On-line emotion recognition in a 3-d activation-valence-time continuum using acoustic and linguistic cues. Journal on Multimodal User Interfaces 3(1-2):7–19. [find](https://scholar.google.com/scholar?q=Florian+Eyben%2C+Martin+Wo%CC%88llmer%2C+Alex+Graves%2C+Bjo%CC%88rn+Schuller%2C+Ellen+Douglas%2DCowie%2C+and+Roddy+Cowie%2E+2010a%2E+On%2Dline+emotion+recognition+in+a+3%2Dd+activation%2Dvalence%2Dtime+continuum+using+acoustic+and+lin)
25. Verónica Pérez-Rosas, Rada Mihalcea, and Louis-Philippe Morency. 2013. Utterance-level multimodal sentiment analysis. In ACL (1). pages 973– 982. [find](https://scholar.google.com/scholar?q=Vero%CC%81nica+Pe%CC%81rez%2DRosas%2C+Rada+Mihalcea%2C+and+Louis%2DPhilippe+Morency%2E+2013%2E+Utterance%2Dlevel+multimodal+sentiment+analysis%2E+In+ACL+%281%29%2E+pages+973%E2%80%93+982%2E)
26. Martin Wöllmer, Florian Eyben, Stephan Reiter, Björn W Schuller, Cate Cox, Ellen Douglas-Cowie, Roddy Cowie, et al. 2008. Abandoning emotion classes-towards continuous emotion recognition with modelling of long-range dependencies. In Interspeech. volume 2008, pages 597–600. [find](https://scholar.google.com/scholar?q=Martin+Wo%CC%88llmer%2C+Florian+Eyben%2C+Stephan+Reiter%2C+Bjo%CC%88rn+W+Schuller%2C+Cate+Cox%2C+Ellen+Douglas%2DCowie%2C+Roddy+Cowie%2C+et+al%2E+2008%2E+Abandoning+emotion+classes%2Dtowards+continuous+emotion+recognition+with+model)
27. Soujanya Poria, Erik Cambria, Rajiv Bajpai, and Amir Hussain. 2017a. A review of affective computing: From unimodal analysis to multimodal fusion. Information Fusion . [find](https://scholar.google.com/scholar?q=Soujanya+Poria%2C+Erik+Cambria%2C+Rajiv+Bajpai%2C+and+Amir+Hussain%2E+2017a%2E+A+review+of+affective+computing%3A+From+unimodal+analysis+to+multimodal+fusion%2E+Information+Fusion+%2E)
28. Soujanya Poria, Erik Cambria, and Alexander Gelbukh. 2015. Deep convolutional neural network textual features and multiple kernel learning for utterance-level multimodal sentiment analysis. In Proceedings of EMNLP. pages 2539–2544. [find](https://scholar.google.com/scholar?q=Soujanya+Poria%2C+Erik+Cambria%2C+and+Alexander+Gelbukh%2E+2015%2E+Deep+convolutional+neural+network+textual+features+and+multiple+kernel+learning+for+utterance%2Dlevel+multimodal+sentiment+analysis%2E+In+Proceed)
29. Martin Wollmer, Felix Weninger, Timo Knaup, Bjorn Schuller, Congkai Sun, Kenji Sagae, and Louis-Philippe Morency. 2013. Youtube movie reviews: Sentiment analysis in an audio-visual context. IEEE Intelligent Systems 28(3):46–53. [find](https://scholar.google.com/scholar?q=Martin+Wollmer%2C+Felix+Weninger%2C+Timo+Knaup%2C+Bjorn+Schuller%2C+Congkai+Sun%2C+Kenji+Sagae%2C+and+Louis%2DPhilippe+Morency%2E+2013%2E+Youtube+movie+reviews%3A+Sentiment+analysis+in+an+audio%2Dvisual+context%2E+IEEE+Intel)
30. Soujanya Poria, Erik Cambria, and Alexander Gelbukh. 2016a. Aspect extraction for opinion mining with a deep convolutional neural network. Knowledge-Based Systems 108:42–49. [find](https://scholar.google.com/scholar?q=Soujanya+Poria%2C+Erik+Cambria%2C+and+Alexander+Gelbukh%2E+2016a%2E+Aspect+extraction+for+opinion+mining+with+a+deep+convolutional+neural+network%2E+Knowledge%2DBased+Systems+108%3A42%E2%80%9349%2E)
31. Chung-Hsien Wu and Wei-Bin Liang. 2011. Emotion recognition of affective speech based on multiple classifiers using acoustic-prosodic information and semantic labels. IEEE Transactions on Affective Computing 2(1):10–21. [find](https://scholar.google.com/scholar?q=Chung%2DHsien+Wu+and+Wei%2DBin+Liang%2E+2011%2E+Emotion+recognition+of+affective+speech+based+on+multiple+classifiers+using+acoustic%2Dprosodic+information+and+semantic+labels%2E+IEEE+Transactions+on+Affective+Co)
32. Soujanya Poria, Erik Cambria, D Hazarika, and Prateek Vij. 2016b. A deeper look into sarcastic tweets using deep convolutional neural networks. In COLING. pages 1601–1612. [find](https://scholar.google.com/scholar?q=Soujanya+Poria%2C+Erik+Cambria%2C+D+Hazarika%2C+and+Prateek+Vij%2E+2016b%2E+A+deeper+look+into+sarcastic+tweets+using+deep+convolutional+neural+networks%2E+In+COLING%2E+pages+1601%E2%80%931612%2E) [our card](https://md.research.elamur.ai/free/en/papers/poria-2016-deeper-look-into-sarcastic-tweets/)
33. Xun Yuan, Wei Lai, Tao Mei, Xian-Sheng Hua, Xiu-Qing Wu, and Shipeng Li. 2006. Automatic video genre categorization using hierarchical svm. In Image Processing, 2006 IEEE International Conference on. IEEE, pages 2905–2908. [find](https://scholar.google.com/scholar?q=Xun+Yuan%2C+Wei+Lai%2C+Tao+Mei%2C+Xian%2DSheng+Hua%2C+Xiu%2DQing+Wu%2C+and+Shipeng+Li%2E+2006%2E+Automatic+video+genre+categorization+using+hierarchical+svm%2E+In+Image+Processing%2C+2006+IEEE+International+Conference+on%2E+)
34. Soujanya Poria, Iti Chaturvedi, Erik Cambria, and Federica Bisio. 2016c. Sentic LDA: Improving on LDA with semantic similarity for aspect-based sentiment analysis. In IJCNN. pages 4465–4473. [find](https://scholar.google.com/scholar?q=Soujanya+Poria%2C+Iti+Chaturvedi%2C+Erik+Cambria%2C+and+Federica+Bisio%2E+2016c%2E+Sentic+LDA%3A+Improving+on+LDA+with+semantic+similarity+for+aspect%2Dbased+sentiment+analysis%2E+In+IJCNN%2E+pages+4465%E2%80%934473%2E)
35. Amir Zadeh, Rowan Zellers, Eli Pincus, and Louis-Philippe Morency. 2016. Multimodal sentiment intensity analysis in videos: Facial gestures and verbal messages. IEEE Intelligent Systems 31(6):82–88. [find](https://scholar.google.com/scholar?q=Amir+Zadeh%2C+Rowan+Zellers%2C+Eli+Pincus%2C+and+Louis%2DPhilippe+Morency%2E+2016%2E+Multimodal+sentiment+intensity+analysis+in+videos%3A+Facial+gestures+and+verbal+messages%2E+IEEE+Intelligent+Systems+31%286%29%3A82%E2%80%9388%2E)
36. Soujanya Poria, Iti Chaturvedi, Erik Cambria, and Amir Hussain. 2016d. Convolutional mkl based multimodal emotion recognition and sentiment analysis. In Data Mining (ICDM), 2016 IEEE 16th International Conference on. IEEE, pages 439–448. [find](https://scholar.google.com/scholar?q=Soujanya+Poria%2C+Iti+Chaturvedi%2C+Erik+Cambria%2C+and+Amir+Hussain%2E+2016d%2E+Convolutional+mkl+based+multimodal+emotion+recognition+and+sentiment+analysis%2E+In+Data+Mining+%28ICDM%29%2C+2016+IEEE+16th+Internationa)
37. Peng Zhou, Wei Shi, Jun Tian, Zhenyu Qi, Bingchen Li, Hongwei Hao, and Bo Xu. 2016. Attention-based bidirectional long short-term memory networks for relation classification. In The 54th Annual Meeting of the Association for Computational Linguistics. pages 207–213. [find](https://scholar.google.com/scholar?q=Peng+Zhou%2C+Wei+Shi%2C+Jun+Tian%2C+Zhenyu+Qi%2C+Bingchen+Li%2C+Hongwei+Hao%2C+and+Bo+Xu%2E+2016%2E+Attention%2Dbased+bidirectional+long+short%2Dterm+memory+networks+for+relation+classification%2E+In+The+54th+Annual+Meetin) [our card](https://md.research.elamur.ai/free/en/papers/zhou-2016-attention-based-bidirectional-long-short/)
38. Soujanya Poria, Haiyun Peng, Amir Hussain, Newton Howard, and Erik Cambria. 2017b. Ensemble application of convolutional neural networks and multiple kernel learning for multimodal sentiment analysis. Neurocomputing . [find](https://scholar.google.com/scholar?q=Soujanya+Poria%2C+Haiyun+Peng%2C+Amir+Hussain%2C+Newton+Howard%2C+and+Erik+Cambria%2E+2017b%2E+Ensemble+application+of+convolutional+neural+networks+and+multiple+kernel+learning+for+multimodal+sentiment+analysis%2E)
39. Dheeraj Rajagopal, Erik Cambria, Daniel Olsher, and Kenneth Kwok. 2013. A graph-based approach to commonsense concept extraction and semantic similarity detection. In WWW. Rio De Janeiro, pages 565–570. [find](https://scholar.google.com/scholar?q=Dheeraj+Rajagopal%2C+Erik+Cambria%2C+Daniel+Olsher%2C+and+Kenneth+Kwok%2E+2013%2E+A+graph%2Dbased+approach+to+commonsense+concept+extraction+and+semantic+similarity+detection%2E+In+WWW%2E+Rio+De+Janeiro%2C+pages+565%E2%80%9357)
40. Viktor Rozgic, Sankaranarayanan Ananthakrishnan, Shirin Saleem, Rohit Kumar, and Rohit Prasad. 2012. Ensemble of svm trees for multimodal emotion recognition. In Signal & Information Processing Association Annual Summit and Conference (APSIPA ASC), 2012 Asia-Pacific. IEEE, pages 1–4. [find](https://scholar.google.com/scholar?q=Viktor+Rozgic%2C+Sankaranarayanan+Ananthakrishnan%2C+Shirin+Saleem%2C+Rohit+Kumar%2C+and+Rohit+Prasad%2E+2012%2E+Ensemble+of+svm+trees+for+multimodal+emotion+recognition%2E+In+Signal+%26+Information+Processing+Associ)
41. Björn Schuller. 2011. Recognizing affect from linguistic information in 3d continuous space. IEEE Transactions on Affective Computing 2(4):192–205. [find](https://scholar.google.com/scholar?q=Bjo%CC%88rn+Schuller%2E+2011%2E+Recognizing+affect+from+linguistic+information+in+3d+continuous+space%2E+IEEE+Transactions+on+Affective+Computing+2%284%29%3A192%E2%80%93205%2E)
42. Richard Socher, Alex Perelygin, Jean Y Wu, Jason Chuang, Christopher D Manning, Andrew Y Ng, and Christopher Potts. 2013. Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of EMNLP. pages 1631–1642. [find](https://scholar.google.com/scholar?q=Richard+Socher%2C+Alex+Perelygin%2C+Jean+Y+Wu%2C+Jason+Chuang%2C+Christopher+D+Manning%2C+Andrew+Y+Ng%2C+and+Christopher+Potts%2E+2013%2E+Recursive+deep+models+for+semantic+compositionality+over+a+sentiment+treebank%2E)
43. Vee Teh and Geoffrey E Hinton. 2001. Rate-coded restricted boltzmann machines for face recognition. In T Leen, T Dietterich, and V Tresp, editors, Advances in neural information processing system. volume 13, pages 908–914. [find](https://scholar.google.com/scholar?q=Vee+Teh+and+Geoffrey+E+Hinton%2E+2001%2E+Rate%2Dcoded+restricted+boltzmann+machines+for+face+recognition%2E+In+T+Leen%2C+T+Dietterich%2C+and+V+Tresp%2C+editors%2C+Advances+in+neural+information+processing+system%2E+vol)