How Intense Are You? Predicting Intensities of Emotions and Sentiments using Stacked Ensemble [Application Notes] (original) (raw)
Related papers
The paper describes the best performing system for EmoInt-a shared task to predict the intensity of emotions in tweets. Intensity is a real valued score, between 0 and 1. The emotions are classified as-anger, fear, joy and sadness. We apply three different deep neural network based models, which approach the problem from essentially different directions. Our final performance quantified by an average pearson correlation score of 74.7 and an average spearman correlation score of 73.5 is obtained using an ensemble of the three models. We outperform the base-line model of the shared task by 9.9% and 9.4% pearson and spearman correlation scores respectively.
Disney at IEST 2018: Predicting Emotions using an Ensemble
Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
This paper describes our participating system in the WASSA 2018 shared task on emotion prediction. The task focuses on implicit emotion prediction in a tweet. In this task, keywords corresponding to the six emotion labels used (anger, fear, disgust, joy, sad, and surprise) have been removed from the tweet text, making emotion prediction implicit and the task challenging. We propose a model based on an ensemble of classifiers for prediction. Each classifier uses a sequence of Convolutional Neural Network (CNN) architecture blocks and uses ELMo (Embeddings from Language Model) as an input. Our system achieves a 66.2% F1 score on the test set. The best performing system in the shared task has reported a 71.4% F1 score.
DeepMiner at SemEval-2018 Task 1: Emotion Intensity Recognition Using Deep Representation Learning
Proceedings of The 12th International Workshop on Semantic Evaluation, 2018
In this paper, we propose a regression system to infer the emotion intensity of a tweet. We develop a multi-aspect feature learning mechanism to capture the most discriminative semantic features of a tweet as well as the emotion information conveyed by each word in it. We combine six types of feature groups: (1) a tweet representation learned by an LSTM deep neural network on the training data, (2) a tweet representation learned by an LSTM network on a large corpus of tweets that contain emotion words (a distant supervision corpus), (3) word embeddings trained on the distant supervision corpus and averaged over all words in a tweet, (4) word and character n-grams, (5) features derived from various sentiment and emotion lexicons, and (6) other hand-crafted features. As part of the word embedding training, we also learn the distributed representations of multi-word expressions (MWEs) and negated forms of words. An SVR regressor is then trained over the full set of features. We evaluate the effectiveness of our ensemble feature sets on the SemEval-2018 Task 1 datasets and achieve a Pearson correlation of 72% on the task of tweet emotion intensity prediction.
2017
Our submission to the WASSA-2017 shared task on the prediction of emotion intensity in tweets is a supervised learning method with extended lexicons of affective norms. We combine three main information sources in a random forrest regressor, namely (1), manually created resources, (2) automatically extended lexicons, and (3) the output of a neural network (CNN-LSTM) for sentence regression. All three feature sets perform similarly well in isolation (≈ .67 macro average Pearson correlation). The combination achieves .72 on the official test set (ranked 2nd out of 22 participants). Our analysis reveals that performance is increased by providing cross-emotional intensity predictions. The automatic extension of lexicon features benefit from domain specific embeddings. Complementary ratings for affective norms increase the impact of lexicon features. Our resources (ratings for 1.6 million twitter specific words) and our implementation is publicly available at http: //www.ims.uni-stuttgar...
Sentimental Analysis and Deep Learning : A Survey
International Journal of Scientific Research in Science, Engineering and Technology, 2020
Sentiment Analysis is an ongoing field of research in text mining. Sentiment Analysis is the computational treatment of opinions, Sentiments, and subjectivity of text. Many recently proposed algorithms enhancements and various Sentiment Analysis applications are investigated and presented briefly in this survey. The related fields to Sentiment Analysis that attracted researchers recently are discussed. The main target of this survey is to give nearly full image of Sentiment Analysis techniques and the related fields with brief details. In recent years machine learning has received greater attention with the success of deep learning. Deep learning can create deep models of complex multivariate structures in structured data. Though deep learning can be characterized in several different ways, the most important is that deep learning can learn higher-order interactions among features using a cascade of many layers. Deep learning has been applied to neural networks and across many fields, with significant successes in many applications. Convolution neural networks, deep belief networks, and many other approaches have been proposed to enhance the abilities of deep structure networks
Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)
In this paper we propose an ensemble based model which combines state of the art deep learning sentiment analysis algorithms like Convolution Neural Network (CNN) and Long Short Term Memory (LSTM) along with feature based models to identify optimistic or pessimistic sentiments associated with companies and stocks in financial texts. We build our system to participate in a competition organized by Semantic Evaluation 2017 International Workshop. We combined predictions from various models using an artificial neural network to determine the opinion towards an entity in (a) Microblog Messages and (b) News Headlines data. Our models achieved a cosine similarity score of 0.751 and 0.697 for the above two tracks giving us the rank of 2nd and 7th best team respectively.
Convolutional Neural Network Multi-Emotion Classifiers
Jordanian Journal of Computers and Information Technology, 2019
Natural languages are universal and flexible, but cannot exist without ambiguity. Having more than one attitude and meaning in the same phrase context is the main cause for word or phrase ambiguity. Most previous work on emotion analysis has only covered single-label classification and neglected the presence of multiple emotion labels in one instance. This paper presents multi-emotion classification in Twitter based on Convolutional Neural Networks (CNNs). The applied features are emotion lexicons, word embeddings and frequency distribution. The proposed networks performance is evaluated using state-of-the-art classification algorithms, achieving a hamming score range from 0.46 to 0.52 on the challenging SemEval2018 Task E-c.
Different Techniques of Sentimental Analysis using Deep Learning
International Journal of Scientific and Research Publications (IJSRP)
World Wide Web like social media forums, review sites and blogs that generate a lot of data the type of users views, feelings, ideas and arguments about various social events, products, products, and politics. Emotions of users exposed to the web has a huge influence on it students, product retailers and politicians. Unstructured the type of data from social media is required for analysis and is well organized and for this purpose, emotional analysis has been required the saw important attention. Emotional analysis is called the textual structure used to distinguish the expressed attitude or emotions in different ways such as negative, positive, favoble, wrong, thumbs up, thumbs down, etc. This is a challenge emotion analysis lacks sufficient label data in the field Indigenous Languages (NLP) Processing. And to solve this problem, Emotional analysis and in-depthlearning strategies have been are integrated because in-depth learning models work for them the ability to read automatically. This Review Paper highlights the latest lessons on the implementation of in-depth learning models such as deep neural networks, convolutional neural networks as well many more to solve various emotional analysis problems such as emotional isolation, problems of different languages, text as well as visual analysis and product review analysis, etc.
Proceedings of the 8th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis
This paper describes the system that we submitted as part of our participation in the shared task on Emotion Intensity (EmoInt-2017). We propose a Long short term memory (LSTM) based architecture cascaded with Support Vector Regressor (SVR) for intensity prediction. We also employ Particle Swarm Optimization (PSO) based feature selection algorithm for obtaining an optimized feature set for training and evaluation. System evaluation shows interesting results on the four emotion datasets i.e. anger, fear, joy and sadness. In comparison to the other participating teams our system was ranked 5th in the competition.
Our submission to the WASSA-2017 shared task on the prediction of emotion intensity in tweets is a supervised learning method with extended lexicons of affective norms. We combine three main information sources in a random forrest regressor, namely (1), manually created resources, (2) automatically extended lexicons, and (3) the output of a neural network (CNN-LSTM) for sentence regression. All three feature sets perform similarly well in isolation (≈ .67 macro average Pearson correlation). The combination achieves .72 on the official test set (ranked 2nd out of 22 participants). Our analysis reveals that performance is increased by providing cross-emotional intensity predictions. The automatic extension of lexicon features benefit from domain specific embeddings. Complementary ratings for affective norms increase the impact of lexicon features. Our resources (ratings for 1.6 million twitter specific words) and our implementation is publicly available at http: //www.ims.uni-stuttgart.de/ data/ims_emoint.