How Intense Are You? Predicting Intensities of Emotions and Sentiments using Stacked Ensemble [Application Notes]

Akhtar, Md. Shad; Ekbal, Asif; Wang, Zhaoxia

doi:10.1109/mci.2019.2954667

Cited by 215 publications

(79 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main subtasks of sentiment classification are emotion identification [ 35 ], sentiment intensity prediction [ 36 ], and polarity detection [ 37 ]. Emotion identification detects the emotions behind sentiments such as anger or sadness.…”

Section: Seopinion: Methodologymentioning

confidence: 99%

SEOpinion: Summarization and Exploration of Opinion from E-Commerce Websites

Mabrouk

Redondo

Kayed

2021

Sensors

View full text Add to dashboard Cite

Recently, it has been found that e-commerce (EC) websites provide a large amount of useful information that exceed the human cognitive processing capacity. In order to help customers in comparing alternatives when buying a product, previous research authors have designed opinion summarization systems based on customer reviews. They ignored the template information provided by manufacturers, although its descriptive information has the most useful product characteristics and texts are linguistically correct, unlike reviews. Therefore, this paper proposes a methodology coined as SEOpinion (summarization and exploration of opinions) to summarize aspects and spot opinion(s) regarding them using a combination of template information with customer reviews in two main phases. First, the hierarchical aspect extraction (HAE) phase creates a hierarchy of aspects from the template. Subsequently, the hierarchical aspect-based opinion summarization (HAOS) phase enriches this hierarchy with customers’ opinions to be shown to other potential buyers. To test the feasibility of using deep learning-based BERT techniques with our approach, we created a corpus by gathering information from the top five EC websites for laptops. The experimental results showed that recurrent neural network (RNN) achieved better results (77.4% and 82.6% in terms of F1-measure for the first and second phases, respectively) than the convolutional neural network (CNN) and the support vector machine (SVM) technique.

show abstract

Section: Seopinion: Methodologymentioning

confidence: 99%

SEOpinion: Summarization and Exploration of Opinion from E-Commerce Websites

Mabrouk

Redondo

Kayed

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Dridi, Atzeni and Recupero [ 42 ] proposed a supervised method and found that semantic features and semantic frames can be applied successfully to sentiment analysis within the financial domain, thus leading to better results. Finally, Akhtar, Ekbal and Cambria [ 46 ] proposed a stacked ensemble method for predicting the degree of intensity for emotion and sentiment by combining the outputs obtained from several deep learning and classical feature-based models using a multi-layer perceptron network. To achieve this, Akhtar and colleagues focused on emotion analysis in the generic domain and sentiment analysis in the financial domain.…”

Section: State Of the Artmentioning

confidence: 99%

Does Twitter Affect Stock Market Decisions? Financial Sentiment Analysis During Pandemics: A Comparative Study of the H1N1 and the COVID-19 Periods

et al. 2021

View full text Add to dashboard Cite

Investors are constantly aware of the behaviour of stock markets. This affects their emotions and motivates them to buy or sell shares. Financial sentiment analysis allows us to understand the effect of social media reactions and emotions on the stock market and vice versa. In this research, we analyse Twitter data and important worldwide financial indices to answer the following question: How does the polarity generated by Twitter posts influence the behaviour of financial indices during pandemics? This study is based on the financial sentiment analysis of influential Twitter accounts and its relationship with the behaviour of important financial indices. To carry out this analysis, we used fundamental and technical financial analysis combined with a lexicon-based approach on financial Twitter accounts. We calculated the correlations between the polarities of financial market indicators and posts on Twitter by applying a date shift on tweets. In addition, correlations were identified days before and after the existing posts on financial Twitter accounts. Our findings show that the markets reacted 0 to 10 days after the information was shared and disseminated on Twitter during the COVID-19 pandemic and 0 to 15 days after the information was shared and disseminated on Twitter during the H1N1 pandemic. We identified an inverse relationship: Twitter accounts presented reactions to financial market behaviour within a period of 0 to 11 days during the H1N1 pandemic and 0 to 6 days during the COVID-19 pandemic. We also found that our method is better at detecting highly shifted correlations by using SenticNet compared with other lexicons. With SenticNet, it is possible to detect correlations even on the same day as the Twitter posts. The most influential Twitter accounts during the period of the pandemic were The New York Times, Bloomberg, CNN News and Investing.com, presenting a very high correlation between sentiments on Twitter and stock market behaviour. The combination of a lexicon-based approach is enhanced by a shifted correlation analysis, as latent or hidden correlations can be found in data.

show abstract

“…This would not have been possible without the benefits of the unstructured bank of social data. Another recent work [34] attempted to predict the intensities of emotions and sentiments through a stacked ensemble method-namely, convolutional neural networks, gated recurrent units, long-and short-term memory, and support vector regression. The proposed model achieved an impressive result, even compared to other state-of-the-art systems.…”

Section: Previous Workmentioning

confidence: 99%

Sentiment Analysis for e-Payment Service Providers Using Evolutionary eXtreme Gradient Boosting

et al. 2020

View full text Add to dashboard Cite

Online services depend primarily on customer feedback and communications. When this kind of input is lacking, the overall approach of the service provider can shift in unintended ways. These services rely on feedback to maintain consumer satisfaction. Online social networks are a rich source of consumer data related to services and products. Well developed methods like sentiment analysis can offer insightful analyses and aid service providers in predicting outcomes based on their reviews-which, in turn, enables decision-makers to develop effective strategic plans. However, gathering this data is more challenging on Arabic online social networks, due to the complexity of the Arabic language and its dialects. In this study, we propose an approach to sentiment analysis that combines a neutrality detector model with eXtreme Gradient Boosting and a genetic algorithm to effectively predict and analyze customers' opinions of an e-Payment service through an Arabic social network. The proposed approach yields excellent results compared to other approaches. Feature analysis is also conducted on consumer reviews to identify influencing keywords.

show abstract

How Intense Are You? Predicting Intensities of Emotions and Sentiments using Stacked Ensemble [Application Notes]

Cited by 215 publications

References 49 publications

SEOpinion: Summarization and Exploration of Opinion from E-Commerce Websites

SEOpinion: Summarization and Exploration of Opinion from E-Commerce Websites

Does Twitter Affect Stock Market Decisions? Financial Sentiment Analysis During Pandemics: A Comparative Study of the H1N1 and the COVID-19 Periods

Sentiment Analysis for e-Payment Service Providers Using Evolutionary eXtreme Gradient Boosting

Contact Info

Product

Resources

About