A survey of multimodal sentiment analysis

Soleymani, Mohammad; García, David; Jou, Brendan; Schuller, Björn; Chang, Shih‐Fu; Pantić, Maja

doi:10.1016/j.imavis.2017.08.003

Cited by 452 publications

(223 citation statements)

References 39 publications

Supporting

Mentioning

187

Contrasting

Unclassified

Order By: Relevance

“…A further subset of tweets (categorized as General) was collected from the stream, without any keyword filters, in order to further broaden the representative scope of our dataset. We additionally filtered out tweets containing external links or images, arguing that analysis of these multimodal tweets is a separate problem, belonging to the domain of Multimodal Sentiment Analysis (Poria et al, 2016;Soleymani et al, 2017). After the entire filtering process 4 was complete, we obtained 7,026 tweets across the different topics, which would be annotated with 5x coverage.…”

Section: Data Collectionmentioning

confidence: 99%

Sentiment Analysis: It’s Complicated!

Kenyon-Dean

Ahmed²,

Fujimoto

et al. 2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: Hu

View full text Add to dashboard Cite

Sentiment analysis is used as a proxy to measure human emotion, where the objective is to categorize text according to some predefined notion of sentiment. Sentiment analysis datasets are typically constructed with gold-standard sentiment labels, assigned based on the results of manual annotations. When working with such annotations, it is common for dataset constructors to discard "noisy" or "controversial" data where there is significant disagreement on the proper label. In datasets constructed for the purpose of Twitter sentiment analysis (TSA), these controversial examples can compose over 30% of the originally annotated data. We argue that the removal of such data is a problematic trend because, when performing real-time sentiment classification of short-text, an automated system cannot know a priori which samples would fall into this category of disputed sentiment. We therefore propose the notion of a "complicated" class of sentiment to categorize such text, and argue that its inclusion in the short-text sentiment analysis framework will improve the quality of automated sentiment analysis systems as they are implemented in real-world settings. We motivate this argument by building and analyzing a new publicly available TSA dataset of over 7,000 tweets annotated with 5x coverage, named MTSA. Our analysis of classifier performance over our dataset offers insights into sentiment analysis dataset and model design, how current techniques would perform in the real world, and how researchers should handle difficult data.

show abstract

Section: Data Collectionmentioning

confidence: 99%

Sentiment Analysis: It’s Complicated!

Kenyon-Dean

Ahmed²,

Fujimoto

et al. 2018

Proceedings of the 2018 Conference of the North American Chapter Of the Association for Computational Linguistics: Hu

View full text Add to dashboard Cite

show abstract

“…As such, it is helpful to combine these modalities of visual, text, and audio modalities for SDA (Pérez‐Rosas, Mihalcea, & Morency, ). Consequently, multimodal SDA has already created a lot of buzzes to better identify true sentiment states (Poria, Cambria, Bajpai, & Hussain, ; Soleymani et al, ), being concerned primarily with a unified representation of cross modalities and modal fusion.…”

Section: Multimodal Fusions Of Sdamentioning

confidence: 99%

A review on sentiment discovery and analysis of educational big‐data

Han

Wu²,

Huang

et al. 2019

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Sentiment discovery and analysis (SDA) aims to automatically identify the underlying attitudes, sentiments, and subjectivity towards a certain entity such as learners and learning resources. Due to its enormous potential for smart education, SDA has been deemed as a powerful technique for identifying and classifying sentiments from multimodal and multisource data over the whole process of education. For big educational data streams, SDA faces challenges in unimodal feature selection, sentiment classification, and multimodal fusion. As such, a large body of studies in the literature explores diverse approaches to SDA for educational applications. This paper provides a self‐contained, uniform overview of the SDA techniques for education. In particular, we focus on prominent studies in unimodal sentiment features and classifications (e.g., text, audio, and visual). In addition, we present a novel SDA framework of multimodal fusions, together with description of their crucial components. Based on this framework, we review different approaches to SDA on education from the perspectives of approaches and applications. After comprehensively reviewing the SDA techniques on education, we present the trends and prospectives of the future SDA research under ubiquitous education contexts. This article is categorized under: Application Areas > Education and Learning

show abstract

“…For instance, in [20] and [26], sentiment analysis is used in order to evaluate short texts coming from Twitter and other resources. On [28], several multimodal sentiment analysis methods are reviewed. Finally, in [16], sentiment analysis is applied in movie reviews.…”

Section: Sentiment Analysismentioning

confidence: 99%

Analysing discussions in social networks using group decision making methods and sentiment analysis

Morente-Molinera

Kou

Peng

et al. 2018

Information Sciences

View full text Add to dashboard Cite

Esta es la versión de autor del artículo publicado en: This is an author produced version of a paper published in:Information Sciences 447 (2018) AbstractSocial networks are one of the most preferred environments for people to carry out debates. Due to the fact that a high amount of people can participate in the process, there is a need of tools that can analyse these discussions and extract useful information from them. In this paper, a novel way of determining how the debate is going on, if there is consensus among the participants and which alternatives are preferred is presented. Sentiment analysis is used in order to measure the level of preference that social media users have about a certain set of alternatives. In order to test the presented scheme, a real application example that makes use of Twitter information is presented.

show abstract

A survey of multimodal sentiment analysis

Cited by 452 publications

References 39 publications

Sentiment Analysis: It’s Complicated!

Sentiment Analysis: It’s Complicated!

A review on sentiment discovery and analysis of educational big‐data

Analysing discussions in social networks using group decision making methods and sentiment analysis

Contact Info

Product

Resources

About