Introducing
Your new presentation assistant.
Refine, enhance, and tailor your content, source relevant images, and edit visuals quicker than ever before.
Trending searches
Emotion Detection and Recognition from text is a recent field of research that is closely related to Sentiment Analysis. Sentiment Analysis aims to detect positive, neutral, or negative feelings from text, whereas Emotion Analysis aims to detect and recognize types of feelings through the expression of texts, such as anger, disgust, fear, happiness, sadness, and surprise. Emotion detection may have useful applications, such as:
The field of ED has also be applied in applications such as emotion retrieval from suicide notes,capturing emotions
in multimedia tagging, detecting insulting sentences in conversations, and so on. However, whereas detecting emotions
from voice/speech, images, and other multimodal methods have an exhaustive knowledge base, there exists great paucity
in research for texts. This is because unlike multimodal methods, texts may not portray peculiar cues to emotions.
Also, the hurdle of detecting emotions from short texts, emojis, and grammatical errors could be back-breaking coupled
with the continuous evolution of new words as a result of language dynamics
Our work represents basic model of ED.
It also introduces the models of emotions and further showcases publicly available data sources for text-based emotion research.
current approaches used for detecting emotions are discussed. Current state-of-the-art techniques are also elucidated . Open issues, possible opportunities, and techniques to improve the detection of emotions in texts
are also discussed.
Web 2.0 are websites and applications that make use of user-generated content for end-users. Web 2.0 is characterized by greater user interactivity and collaboration, more pervasive network connectivity and enhanced communication channels.
Most of the technologies used in delivering web 2.0 are rich Web technologies, such as Adobe Flash, Microsoft Silverlight and JavaScript (in addition to Ajax, RSS and Eclipse).
We use ED1,
ED2, ED3 up to ED11 to represent ED search results for the year 2010, 2011, 2012 up to 2020, respectively, and TB1, TB2,
TB3 up to TB11 to represent text-based ED search results, respectively
ALGORITHM
Graph showing the disparity of research in
emotion detection and emotion detection from texts in IEEE Xplore Database
Graph showing the disparity of research in
emotion detection and emotion detection from texts in Scopus Database
Emotion models are the foundations of ED systems; they define how emotions are represented. The models assume that
emotions exist in various states thus the need to distinguish between the various emotion states. When undertaking
any ED related activity, it is imperative to initially define the model of emotion for use. In Reference 13, various forms
of representing emotions are identified; however, of utmost importance to this article is the discrete and dimensional
emotion models (DEMs and DiEMs, respectively).
A comprehensive guide to the subfield of SA/ED specifically text-based ED has been presented. The article
introduces the concept of text-based ED, emotion models, and highlights some important datasets available for text-based
ED research. The three main approaches utilized when designing text-based ED systems have been elucidated, together
with their strengths and weaknesses. The article further discusses current state-of-the-art with emphasis on their applied
approaches, datasets used, major contributions, and limitations. Finally, the article presents open issues and future
research directions for researchers in the domain of text-based ED.