Document Level Sentiment Analysis from News Articles

Shirsat, Vishal S.; Jagdale, Rajkumar S.; Deshmukh, Sachin N.

doi:10.1109/iccubea.2017.8463638

Cited by 30 publications

(14 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kim et al [24] proposed a new language model by combining CNN, LSTM, and highway network. Similarly for document-level classification, Moraes et al [28] done empirical comparative study for documents-level sentiment classification and there are some others works too have been done in sentiment analysis at the document-level [29], [30]. The joint architecture model for document classification to have been proposed.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning Based Weighted Feature Fusion Approach for Sentiment Analysis

et al. 2019

View full text Add to dashboard Cite

Deep learning algorithms have achieved remarkable results in the natural language processing(NLP) and computer vision. Hence, a trend still going on to use these algorithms, such as convolution and recurrent neural networks, for text analytic task to extract useful information. Features extraction is one of the important reasons behind the success of these networks. Moreover passing features from one layer to another layer within the network and one network to another network have done. However multilevel and multitype features fusion remains unexplored in sentiment analysis. So, in this paper, we use three datasets to display the advantages of extracting and fusing multilevel as well as multitype features from different neural networks. Multilevel features are from different layers of the same network, and multitype features are from different network architectures. Experiment results demonstrate that the proposed model based on multilevel and multitype weighted features fusion outperforms than many exiting works with an accuracy of 80.2%, 48.2%, and 87.0% on MR, SST1, and SST2 datasets respectively.INDEX TERMS Convolution neural network, recurrent neural network, feature fusion, feature learning, and sentiment analysis.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Learning Based Weighted Feature Fusion Approach for Sentiment Analysis

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Sentiment analysis is the task of identifying positive and negative opinions, emotions, and evaluations (Wilson et al, 2005). Two researchers read all texts and identified the predominant sentiment (positive, negative or neutral) through document-level analysis (Shirsat et al, 2017). The task at this level is to determine the overall opinion of the document.…”

Section: Methodsmentioning

confidence: 99%

When governments spread lies, the fight is against two viruses: A study on the novel coronavirus pandemic in Brazil

Biancovilli

Jurberg

2020

Preprint

View full text Add to dashboard Cite

Background: One of the challenges posed by the novel coronavirus pandemic is the infodemic risk, that is, a huge amount of information being published on the topic, along with misinformation and rumours. Around 100 million people in Brazil (50% of the inhabitants) are users of social media networks, and a substantial amount of false information about the disease circulates in these media. Objectives: In this study, we examine the agenda-setting, media frame and content of misinformation published on the topic. Methods: We analysed all pieces of misinformation published by the Brazilian fact-checking service Lupa Agency during six months of 2020. We used content analysis to classify the texts into categories, and three types of rumours were identified: Misleading content; fabricated content; false context. Results: We analysed 232 pieces of misinformation. Most were published on Facebook (76%), followed by Whatsapp, with 10% of total cases. Half of the stories (47%) are classified as real-life, that is, the focus is on everyday situations, or circumstances involving people. Regarding the type of misinformation, there is a preponderance of fabricated content, with 53% of total, followed by false context (34%) and misleading content (13%). Wrong information was mostly published in text format (47%). We discuss the influence that misinformation can have on the behaviour of the Brazilian population during the pandemic and how the media's agenda-setting is influenced by false information published on social media. Conclusions: This study shows that misinformation about COVID-19 in Brazil seem to help establish an agenda-setting in the country, and the media frame is aligned with President Bolsonaro's political position.

show abstract

“…The analysis of the sentiment, or in general of the opinion, can be performed at different levels of detail, from the most generic to the most specific: document-level, sentence-level, aspect-level, and concept-level (Hemmatian and Sohrabi 2019;Pontiki et al 2016;Nakov et al 2016;Rosenthal et al 2017). The document-level analysis [sometimes referred to as text-level (Pontiki et al 2016)] aims at understanding the polarity of a whole document [e.g., reviews (Behdenna et al 2018), news article (Shirsat et al 2017), a post, a tweet (Gurini et al 2013)]. Therefore, the information is quite general since it summarizes the polarity of many sentences as a unique positive or negative score [usually measured on a two-point or five-point scale (Nakov et al 2016)].…”

Section: Sentiment Analysis: Levels Of Analysismentioning

confidence: 99%

KnowMIS-ABSA: an overview and a reference model for applications of sentiment analysis and aspect-based sentiment analysis

D’Aniello

Rocca

2022

Artif Intell Rev

View full text Add to dashboard Cite

The analysis of the opinions of customers and users has been always of great interest in supporting decision-making in many fields, especially in marketing. Sentiment analysis (SA) is the umbrella term for techniques and approaches that analyze user’s sentiments, emotions, opinions in text or other media. The need for a better understanding of these opinions paved the way to novel approaches that focus on the analysis of the sentiment related to specific features of a product, giving birth to the field of aspect-based sentiment analysis (ABSA). Although the increasing interest in this discipline, there is still confusion regarding the basic concepts of ABSA: terms like sentiment, affect, emotion, opinion, are used as synonyms while they represent different concepts. This often leads to an incorrect analysis of the users’ opinions.This work presents an overview of the state-of-the-art techniques and approaches for ABSA, highlighting the main critical issues related to current trends in this field. Following this analysis, a new reference model for SA and ABSA, namely the KnowMIS-ABSA model, is proposed. The model is grounded on the consideration that sentiment, affect, emotion and opinion are very different concepts and that it is profoundly wrong to use the same metric and the same technique to measure them. Accordingly, we argue that different tools and metrics should be adopted to measure each of the dimensions of an opinion. A qualitative case study, regarding product reviews, is proposed to motivate the advantages of the KnowMIS-ABSA model.

show abstract

Document Level Sentiment Analysis from News Articles

Cited by 30 publications

References 7 publications

Deep Learning Based Weighted Feature Fusion Approach for Sentiment Analysis

Deep Learning Based Weighted Feature Fusion Approach for Sentiment Analysis

When governments spread lies, the fight is against two viruses: A study on the novel coronavirus pandemic in Brazil

KnowMIS-ABSA: an overview and a reference model for applications of sentiment analysis and aspect-based sentiment analysis

Contact Info

Product

Resources

About