Sarcasm Detection Using Multi-Channel Attention Based BLSTM On News Headline

2020 ◽  
Author(s):  
Azika Syahputra Azwar ◽  
Suharjito
Keyword(s):  
Neural Network ◽  
Social Media ◽  
Natural Language ◽  
Sentiment Analysis ◽  
Important Task ◽  
Hybrid Neural Network ◽  
Negative Opinion ◽  
Proposed Model ◽  
Short Memory ◽  
Literary Devices

Abstract Sarcasm is often used to express a negative opinion using positive or intensified positive words in social media. This intentional ambiguity makes sarcasm detection, an important task of sentiment analysis. Detecting a sarcastic tone in natural language hinders the performance of sentiment analysis tasks. The majority of the studies on automatic sarcasm detection emphasize on the use of lexical, syntactic, or pragmatic features that are often unequivocally expressed through figurative literary devices such as words, emoticons, and exclamation marks. In this paper, we introduce a multi-channel attention-based bidirectional long-short memory (MCAB-BLSTM) network to detect sarcastic headline on the news. Multi-channel attention-based bidirectional long-short memory (MCAB-BLSTM) proposed model was evaluated on the news headline dataset, and the results-compared to the CNN-LSTM and Hybrid Neural Network were excellent.

Predicting the French Stock Market Using Social Media Analysis

2015 ◽  
Vol 7 (2) ◽  
pp. 70-84
Author(s):  
Vincent Martin ◽  
Emmanuel Bruno ◽  
Elisabeth Murisasco
Keyword(s):  
Neural Network ◽  
Social Media ◽  
Stock Market ◽  
Sentiment Analysis ◽  
Media Analysis ◽  
Percentage Error ◽  
Social Media Analysis ◽  
Single Output ◽  
The Neural Network ◽  
Simple Neural Network

In this article, the authors try to predict the next-day CAC40 index. They apply the idea of Johan Bollen et al. from (Bollen, Mao, & Zeng, 2011) on the French stock market and they conduct their experiment using French tweets. Two analyses are applied on tweets: sentiment analysis and subjectivity analysis. Results of these analyses are then used to train a simple neural network. The input features are the sentiment, the subjectivity and the CAC40 closing value at day-1 and day-0. The single output value is the predicted CAC40 closing value at day+1. The authors propose an architecture using the JEE framework resulting in a better scalability and an easier industrialization. The main experiments are conducted over 5 months of data. The authors train their neural network on the first of the data and they test predictions on the remaining quarter. Their best run gives a direction accuracy of 80% and a mean absolute percentage error (MAPE) of 2.97%. In another experiment, the authors retrain the neural network each day which decreases the MAPE to 1.14%.

Deep Learning Techniques for Polarity Classification in Multimodal Sentiment Analysis

2018 ◽  
Vol 17 (03) ◽  
pp. 883-910 ◽  
Author(s):  
P. D. Mahendhiran ◽  
S. Kannimuthu
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Natural Language ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Relevant Information ◽  
Neural Net ◽  
Video Information ◽  
Automatic Feature Extraction ◽  
Multimodal Sentiment Analysis

Contemporary research in Multimodal Sentiment Analysis (MSA) using deep learning is becoming popular in Natural Language Processing. Enormous amount of data are obtainable from social media such as Facebook, WhatsApp, YouTube, Twitter and microblogs every day. In order to deal with these large multimodal data, it is difficult to identify the relevant information from social media websites. Hence, there is a need to improve an intellectual MSA. Here, Deep Learning is used to improve the understanding and performance of MSA better. Deep Learning delivers automatic feature extraction and supports to achieve the best performance to enhance the combined model that integrates Linguistic, Acoustic and Video information extraction method. This paper focuses on the various techniques used for classifying the given portion of natural language text, audio and video according to the thoughts, feelings or opinions expressed in it, i.e., whether the general attitude is Neutral, Positive or Negative. From the results, it is perceived that Deep Learning classification algorithm gives better results compared to other machine learning classifiers such as KNN, Naive Bayes, Random Forest, Random Tree and Neural Net model. The proposed MSA in deep learning is to identify sentiment in web videos which conduct the poof-of-concept experiments that proved, in preliminary experiments using the ICT-YouTube dataset, our proposed multimodal system achieves an accuracy of 96.07%.

Deep Persian sentiment analysis: Cross-lingual training for low-resource languages

2020 ◽  
pp. 016555152096278
Author(s):  
Rouzbeh Ghasemi ◽  
Seyed Arad Ashrafi Asli ◽  
Saeedeh Momtazi
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Training Data ◽  
Target Language ◽  
Low Resource ◽  
Proposed Model ◽  
Significant Difference ◽  
Cross Lingual

With the advent of deep neural models in natural language processing tasks, having a large amount of training data plays an essential role in achieving accurate models. Creating valid training data, however, is a challenging issue in many low-resource languages. This problem results in a significant difference between the accuracy of available natural language processing tools for low-resource languages compared with rich languages. To address this problem in the sentiment analysis task in the Persian language, we propose a cross-lingual deep learning framework to benefit from available training data of English. We deployed cross-lingual embedding to model sentiment analysis as a transfer learning model which transfers a model from a rich-resource language to low-resource ones. Our model is flexible to use any cross-lingual word embedding model and any deep architecture for text classification. Our experiments on English Amazon dataset and Persian Digikala dataset using two different embedding models and four different classification networks show the superiority of the proposed model compared with the state-of-the-art monolingual techniques. Based on our experiment, the performance of Persian sentiment analysis improves 22% in static embedding and 9% in dynamic embedding. Our proposed model is general and language-independent; that is, it can be used for any low-resource language, once a cross-lingual embedding is available for the source–target language pair. Moreover, by benefitting from word-aligned cross-lingual embedding, the only required data for a reliable cross-lingual embedding is a bilingual dictionary that is available between almost all languages and the English language, as a potential source language.

scholarly journals In Silico Method for Sentiment and Emotion Analysis in Medicine Using Social Media (Preprint)

2020 ◽  
Author(s):  
Anne Xuan-Lan Nguyen ◽  
Xuan-Vi Trinh ◽  
Sophia Y. Wang ◽  
Albert Y. Wu
Keyword(s):  
Social Media ◽  
Natural Language ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Free Text ◽  
Emotion Analysis ◽  
Search Terms ◽  
Patient Values ◽  
Ibm Watson ◽  
Medical Subspecialty

BACKGROUND Clinical data present in social media is an underused source of information with great potential to allow for a deeper understanding of patient values, attitudes and preferences. OBJECTIVE We describe a novel and broadly applicable method for sentiment analysis and emotion detection to free text from online medical health forums and the factors to consider during its application. METHODS We mined the full discussion and user information of all posts containing search terms related to a specific medical subspecialty (oculoplastics) from MedHelp, the largest online platform for patient health forums. We employed a variety of data cleaning and processing to define the relevant subset of results and prepare those results for sentiment analysis. We executed sentiment and emotion analysis through IBM Watson Natural Language Understanding service to generate sentiment and emotion scores for the posts and their associated keywords. Keywords were aggregated using natural language processing tools. RESULTS 39 oculoplastics-related search terms resulted in 46,381 eligible posts within 14,329 threads, written by 18,319 users (117 doctors; 18,202 patients) and 201,611 associated keywords. Keywords that occurred ≥500 times in the corpus were used to identify most prominent topics, including specific symptoms, medication and complications. The sentiment and emotion scores of these keywords and eligible posts were further analyzed to provide concrete examples of the methodology’s potential to allow better understanding of patients’ attitudes. CONCLUSIONS This comprehensive report allows physicians and researchers to efficiently mine and perform sentiment analysis on social media to better understand patients’ perspectives and promote patient-centric care. Important factors to be considered during application include evaluating the scope of the search, selecting search terms and understanding their different linguistic usages, and establishing robust selection, filtering and processing criteria for posts and keywords tailored to the results.

scholarly journals An Exploration of Impact of COVID 19 on mental health -Analysis of tweets using Natural Language Processing techniques

2020 ◽  
Author(s):  
Sohini Sengupta ◽  
Sareeta Mugde ◽  
Garima Sharma
Keyword(s):  
Mental Health ◽  
Social Media ◽  
Natural Language Processing ◽  
Natural Language ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Gold Mine ◽  
Social Media Platforms ◽  
Processing Techniques

Twitter is one of the world's biggest social media platforms for hosting abundant number of user-generated posts. It is considered as a gold mine of data. Majority of the tweets are public and thereby pullable unlike other social media platforms. In this paper we are analyzing the topics related to mental health that are recently (June, 2020) been discussed on Twitter. Also amidst the on-going pandemic, we are going to find out if covid-19 emerges as one of the factors impacting mental health. Further we are going to do an overall sentiment analysis to better understand the emotions of users.

scholarly journals IMPLEMENTATION OF BACKPROPAGATION NEURAL NETWORK IN SENTIMENT ANALYSIS ON TWITTER TO PUBLIC FIGURES

Compiler ◽  
2020 ◽  
Vol 9 (2) ◽  
pp. 101
Author(s):  
Achmad Safruddin ◽  
Arief Hermawan ◽  
Adityo Permana Wibowo
Keyword(s):  
Neural Network ◽  
Social Media ◽  
Sentiment Analysis ◽  
Test Data ◽  
Text Processing ◽  
Correct Classification ◽  
Backpropagation Neural Network ◽  
Public Figures ◽  
Twitter Users ◽  
Topic Sentiment

Sentiment analysis is a process for identifying or analyzing people's opinions on a topic. Sentiment analysis analyzes each word in a sentence to find out the opinions or sentiments expressed in the sentence. The opinions expressed can be in the form of positive or negative opinions. Twitter is one of the most popular social media in Indonesia. Twitter users always discuss various kinds of topics every day. One of the things discussed on Twitter and which has become a trending topic several times is about public figures. This study discusses the analysis of positive or negative sentiments towards public figures based on tweet data carried out by text processing. The results of text processing are classified using a backpropagation neural network. Tests were carried out using 69 test data, resulting in an accuracy of 62.3%, with 43 correct classification results.

USING OF LSTM NETWORKS IN SENTIMENT ANALYSIS OF DOCUMENTS IN KAZAKH LANGUAGE

2020 ◽  
Vol 69 (1) ◽  
pp. 366-370
Author(s):  
N.K. Kadyrbek ◽  
◽  
М.Е. Mansurova ◽  
М.Е. Kyrgyzbayeva ◽  
◽  
...  
Keyword(s):  
Neural Network ◽  
Social Networks ◽  
Social Media ◽  
Sentiment Analysis ◽  
Mobile Phones ◽  
User Reviews ◽  
Average Value ◽  
First Case ◽  
The Neural Network

Due to the growing trust in information in social media resources, interest in the field of sentiment analysis is growing. Because sentiment analysis is one of the main technologies for monitoring the opinions of millions of users of social networks. The article discusses the use of LSTM networks in the analysis of the tonality of texts in the Kazakh language. For training the neural network, 1000 user reviews of mobile phones were used. The experiments were carried out in two ways: in the first case, preprocessing of the analyzed reviews was carried out, in the second case, the preprocessing was not carried out. The average value of the metric for assessing the quality of the pre-processed model reached 80%. This indicator is 11% higher than for a model trained on data without preprocessing. The results of the study allowed us to conclude that the preprocessing of the texts improves the quality of the model.

Deep Learning Approaches for Textual Sentiment Analysis

2020 ◽  
pp. 171-182 ◽  
Author(s):  
Tamanna Sharma ◽  
Anu Bajaj ◽  
Om Prakash Sangwan
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Sentiment Analysis ◽  
Language Processing ◽  
Machine Learning Techniques ◽  
Computational Technique ◽  
Learning Techniques

Sentiment analysis is computational measurement of attitude, opinions, and emotions (like positive/negative) with the help of text mining and natural language processing of words and phrases. Incorporation of machine learning techniques with natural language processing helps in analysing and predicting the sentiments in more precise manner. But sometimes, machine learning techniques are incapable in predicting sentiments due to unavailability of labelled data. To overcome this problem, an advanced computational technique called deep learning comes into play. This chapter highlights latest studies regarding use of deep learning techniques like convolutional neural network, recurrent neural network, etc. in sentiment analysis.

Sign in / Sign up

Export Citation Format

Share Document