Emotion recognition and brain mapping for sentiment analysis: A review

Hulliyah, Khodijah; Bakar, Normi Sham Awang Abu; Ismail, Amelia Ritahani

doi:10.1109/iac.2017.8280568

Cited by 25 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even if it is a relatively recent area, the automatic detection of emotion in text is an active research field where a variety of tools and methods have been developed with the aim of tackling this task [6], [7]. In spite of this, the effective analysis and treatment of subjective data still represent an important challenge to overcome, since textual emotion detection task presents inherent problems.…”

Section: Related Workmentioning

confidence: 99%

“…There are different techniques applied by NLP researchers to tackle the textual ER task, including the use of Machine Learning (ML), rule-based methods and lexical approaches [6], [7]. However, the majority of such proposals has been performed with machine learning algorithms mainly due to their scalability, learning capacity and fast development.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

EmoLabel: Semi-Automatic Methodology for Emotion Annotation of Social Media Text

Canales

Daelemans

Boldrini

et al. 2022

IEEE Trans. Affective Comput.

View full text Add to dashboard Cite

The exponential growth of the amount of subjective information on the Web 2.0. has caused an increasing interest from researchers willing to develop methods to extract emotion data from these new sources. One of the most important challenges in textual emotion detection is the gathering of data with emotion labels because of the subjectivity of assigning these labels. Basing on this rationale, the main objective of our research is to contribute to the resolution of this important challenge. This is tackled by proposing EmoLabel: a semi-automatic methodology based on pre-annotation, which consists of two main phases: (1) an automatic process to pre-annotate the unlabelled English sentences; and (2) a manual process of refinement where human annotators determine which is the dominant emotion. Our objective is to assess the influence of this automatic pre-annotation method on manual emotion annotation from two points of view: agreement and time needed for annotation. The evaluation performed demonstrates the benefits of pre-annotation processes since the results on annotation time show a gain of near 20% when the pre-annotation process is applied (Pre-ML) without reducing annotator performance. Moreover, the benefits of pre-annotation are higher in those contributors whose performance is low (inaccurate annotators).

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

EmoLabel: Semi-Automatic Methodology for Emotion Annotation of Social Media Text

Canales

Daelemans

Boldrini

et al. 2022

IEEE Trans. Affective Comput.

View full text Add to dashboard Cite

show abstract

“…These are as follows. First, each person's expression of the same or similar sentiment is different, especially in Chinese [19][20][21]. An exclamation or even a punctuation change can cause a reversal of text sentiment, which leads to difficulties in text annotation.…”

Section: Text Sentiment Analysismentioning

confidence: 99%

Exploring the Relationship between Urban Youth Sentiment and the Built Environment Using Machine Learning and Weibo Comments

Duan

Shen

Luo

2022

IJERPH

View full text Add to dashboard Cite

As the relationship between the built environment and the sense of human experience becomes increasingly important, emotional geography has begun to focus on sentiments in space and time and improving the quality of urban construction from the perspective of public emotion and mental health. While youth is a powerful force in urban construction, there are no studies on the relationship between urban youth sentiments and the built environment. With the development of the Internet, social media has provided a large source of data for the metrics of youth sentiment. Based on data from more than 10,000 geolocated Sina Weibo comments posted over one week (from 19 to 25 July 2021) in Shanghai and using a machine learning algorithm for attention mechanism, this study calculates the sentiment label and sentiment intensity of each comment. Ten elements in five aspects were selected to assess the built environment at different scales and also to explore the correlations between built environment elements and sentiment intensity at different scales. The study finds that the overall sentiment of Shanghai youth tends to be negative. Sentiment intensity is significantly associated with most built environment elements at smaller scales. Urban youth have a higher proportion of both happy and sad sentiments, within which sad sentiments are more closely related to the built environment and are significantly related to all built environment elements. This study uses a deep learning algorithm to improve the accuracy of sentiment classification and confirms that the built environment has a great impact on sentiment. This research can help cities develop built environment optimization measures and policies to create positive emotional environments and enhance the well-being of urban youth.

show abstract

“…An alternative approach is the learning-based method. In the learning-based method, the recently trained classifier which applies a specific machine learning model recognizes emotion from a new text input [21][22][23].…”

Section: Introductionmentioning

confidence: 99%

A New Feature Selection Scheme for Emotion Recognition from Text

2020

View full text Add to dashboard Cite

This paper presents a new scheme for term selection in the field of emotion recognition from text. The proposed framework is based on utilizing moderately frequent terms during term selection. More specifically, all terms are evaluated by considering their relevance scores, based on the idea that moderately frequent terms may carry valuable information for discrimination as well. The proposed feature selection scheme performs better than conventional filter-based feature selection measures Chi-Square and Gini-Text in numerous cases. The bag-of-words approach is used to construct the vectors for document representation where each selected term is assigned the weight 1 if it exists or assigned the weight 0 if it does not exist in the document. The proposed scheme includes the terms that are not selected by Chi-Square and Gini-Text. Experiments conducted on a benchmark dataset show that moderately frequent terms boost the representation power of the term subsets as noticeable improvements are observed in terms of Accuracies.

show abstract

Emotion recognition and brain mapping for sentiment analysis: A review

Cited by 25 publications

References 13 publications

EmoLabel: Semi-Automatic Methodology for Emotion Annotation of Social Media Text

EmoLabel: Semi-Automatic Methodology for Emotion Annotation of Social Media Text

Exploring the Relationship between Urban Youth Sentiment and the Built Environment Using Machine Learning and Weibo Comments

A New Feature Selection Scheme for Emotion Recognition from Text

Contact Info

Product

Resources

About