Contextual Utterance Level Multimodal Sentiment Analysis

Context-Dependent Sentiment Analysis in User-Generated Videos
Alternatives To Contextual Utterance Level Multimodal Sentiment Analysis
Project NameStarsDownloadsRepos Using ThisPackages Using ThisMost Recent CommitTotal ReleasesLatest ReleaseOpen IssuesLicenseLanguage
Generating Reviews Discovering Sentiment1,361
4 years ago28mitPython
Code for "Learning to Generate Reviews and Discovering Sentiment"
Awesome Sentiment Analysis770
5 years agocc-by-sa-4.0
😀😄😂😭 A curated list of Sentiment Analysis methods, implementations and misc. 😥😟😱😤
Aspect Based Sentiment Analysis288
2 years agomit
A paper list for aspect based sentiment analysis.
Awesome Nlp Sentiment Analysis275
3 years agogpl-3.0
:book: 收集NLP领域相关的数据集、论文、开源实现,尤其是情感分析、情绪原因识别、评价对象和评价词抽取方面。
a year ago2
Worth-reading papers and related awesome resources on aspect-based sentiment analysis (ABSA). 值得一读的方面级情感分析论文与相关资源集合
7 years ago4
A Chinese sentiment dataset may be useful for sentiment analysis.
2 years ago3March 07, 201711apache-2.0Python
Code and data for inducing domain-specific sentiment lexicons.
Sa Papers108
5 years ago
📄 Deep Learning 中 Sentiment Analysis 論文統整與分析 😀😡☹️😭🙄🤢
Contextual Utterance Level Multimodal Sentiment Analysis97
2 years ago1Python
Context-Dependent Sentiment Analysis in User-Generated Videos
Vista Net82
2 months ago4mitPython
Code for the paper "VistaNet: Visual Aspect Attention Network for Multimodal Sentiment Analysis", AAAI'19
Alternatives To Contextual Utterance Level Multimodal Sentiment Analysis
Select To Compare

Alternative Project Comparisons

Notice: This repository will no longer be maintained. Instead, we are are moving all our multimodal works to this new centralized repository: declare-lab/multimodal-deep-learning.

Context-Dependent Sentiment Analysis in User-Generated Videos

Code for the paper Context-Dependent Sentiment Analysis in User-Generated Videos (ACL 2017).

NOTE: Here is the updated version of the code - soujanyaporia/multimodal-sentiment-analysis


Code is written in Python (2.7) and requires Keras (2.0.6) with Theano backend.


In this paper, we propose a LSTM-based model that enables utterances to capture contextual information from their surroundings in the same video, thus aiding the classification process in multimodal sentiment analysis.

Alt text

This repository contains the code for the mentioned paper. Each contextual LSTM (Figure 2 in the paper) is implemented as shown in above figure. For more details, please refer to the paper.
Note: Unlike the paper, we haven't used an SVM on the penultimate layer. This is in effort to keep the whole network differentiable at some performance cost.


We provide results on the MOSI dataset
Please cite the creators


As data is typically present in utterance format, we combine all the utterances belonging to a video using the following code


Note: This will create speaker independent train and test splits

Running sc-lstm

Sample command:

python --unimodal True
python --unimodal False

Note: Keeping the unimodal flag as True (default False) shall train all unimodal lstms first (level 1 of the network mentioned in the paper)


If using this code, please cite our work using :

  title={Context-dependent sentiment analysis in user-generated videos},
  author={Poria, Soujanya  and Cambria, Erik and Hazarika, Devamanyu and Mazumder, Navonil and Zadeh, Amir and Morency, Louis-Philippe},
  booktitle={Association for Computational Linguistics},


Devamanyu Hazarika, Soujanya Poria

Popular Sentiment Projects
Popular Paper Projects
Popular Machine Learning Categories
Related Searches

Get A Weekly Email With Trending Projects For These Categories
No Spam. Unsubscribe easily at any time.
Sentiment Analysis
Lstm Neural Networks