• Corpus ID: 189928509

Attention-based Modeling for Emotion Detection and Classification in Textual Conversations

  title={Attention-based Modeling for Emotion Detection and Classification in Textual Conversations},
  author={Waleed Ragheb and J{\'e}r{\^o}me Az{\'e} and Sandra Bringay and Maximilien Servajean},
This paper addresses the problem of modeling textual conversations and detecting emotions. [] Key Method The approach does not rely on any hand-crafted features or lexicons. Our model was evaluated on the data provided by the SemEval-2019 shared task on contextual emotion detection in text. The model shows very competitive results.

Figures and Tables from this paper

Emotion Detection of Contextual Text using Deep learning
This system used the Long short term memory (LSTM) model based on deep learning to detect the emotions like happy, sad and angry in contextual conversation to detect emotions from textual dialogues.
AdCOFE: Advanced Contextual Feature Extraction in conversations for emotion classification
Experiments on emotion recognition in conversations datasets show that AdCOFE is beneficial in capturing emotions in conversations.
A Review of Different Approaches for Detecting Emotion from Text
A survey of existing approaches, models, datasets, lexicons, metrics and their limitations in the detection of emotions from the text useful for researchers in carrying out emotion detection activities is provided.
DeepEmotex: Classifying Emotion in Text Messages using Deep Transfer Learning
Transfer learning has been widely used in natural language processing through deep pretrained language models, such as Bidirectional Encoder Representations from Transformers and Universal Sentence
Recognizing Emotions from Texts using a Bert-Based Approach
The paper analyses the efficacy of utilizing transformer encoders on the ISEAR dataset for detecting emotions and proposes a two-stage architecture that becomes the new state-of-the-art in detecting emotions on theISEAR dataset.
Automatic Persian Text Emotion Detection using Cognitive Linguistic and Deep Learning
A System which is based on combination of cognitive features and deep neural network, Gated Recurrent Unit has been proposed in this paper and shows the improvement of several percent’s in comparison by other results achieved GRU and cognitive features in isolation.
Emotion Recognition in Conversation: Research Challenges, Datasets, and Recent Advances
These challenges in ERC are discussed, the drawbacks of these approaches are described, and the reasons why they fail to successfully overcome the research challenges are discussed.
Attention uncovers task-relevant semantics in emotional narrative understanding
Text‐based emotion detection: Advances, challenges, and opportunities
The concept of ED from texts is surveyed and the main approaches adopted by researchers in the design of text‐based ED systems are highlighted and some recent state‐of‐the‐art proposals in the field are discussed.


DialogueRNN: An Attentive RNN for Emotion Detection in Conversations
A new method based on recurrent neural networks that keeps track of the individual party states throughout the conversation and uses this information for emotion classification and outperforms the state of the art by a significant margin on two different datasets.
SemEval-2019 Task 3: EmoContext Contextual Emotion Detection in Text
The analysis of systems submitted to the task indicate that Bi-directional LSTM was the most common choice of neural architecture used, and most of the systems had the best performance for the Sad emotion class, and the worst for the Happy emotion class.
EmoTxt: A toolkit for emotion recognition from text
EmoTxt, the first open-source toolkit supporting both emotion recognition from text and training of custom emotion classification models, is presented, and empirical evidence of the performance of EmoTxt is provided.
Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
This paper proposes Emotional Chatting Machine (ECM), the first work that addresses the emotion factor in large-scale conversation generation using three new mechanisms that respectively models the high-level abstraction of emotion expressions by embedding emotion categories.
Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM
A novel solution to targeted aspect-based sentiment analysis, which tackles the challenges of both aspect- based sentiment analysis and targeted sentiment analysis by exploiting commonsense knowledge by augmenting the LSTM network with a hierarchical attention mechanism.
It is shown how the combined strength and wisdom of the crowds can be used to generate a large, high‐quality, word–emotion and word–polarity association lexicon quickly and inexpensively.
Word Affect Intensities
This work creates an affect intensity lexicon with real-valued scores of association, using a technique called best-worst scaling that improves annotation consistency and obtains reliable fine-grained scores.
Recent Trends in Deep Learning Based Natural Language Processing [Review Article]
This paper reviews significant deep learning related models and methods that have been employed for numerous NLP tasks and provides a walk-through of their evolution.
Regularizing and Optimizing LSTM Language Models
This paper proposes the weight-dropped LSTM which uses DropConnect on hidden-to-hidden weights as a form of recurrent regularization and introduces NT-ASGD, a variant of the averaged stochastic gradient method, wherein the averaging trigger is determined using a non-monotonic condition as opposed to being tuned by the user.