Hope speech detection in YouTube comments

Chakravarthi, Bharathi Raja

doi:10.1007/s13278-022-00901-z

Cited by 21 publications

(3 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Preliminary works on detecting sentiment in YouTube comments have vastly focused on using data with annotated sentiment classes [27]. These papers examine the use of machine learning models to predict the sentiment of new comments based on previously trained data [28].…”

Section: Youtubementioning

confidence: 99%

Subjectivity Analysis for Aspect-based Sentiment and Opinion Detection of YouTube Product Reviews

Tetteh,

Thushara

2023

Preprint

View full text Add to dashboard Cite

The advent of the internet has presented a novel paradigm for conducting consumer research and focus group investigations. Social media platforms enable organizations and entities to efficiently obtain and analyze public opinions regarding their products and services. This eliminates the need for extensive resource allocation towards traditional survey methods and information-gathering strategies. The present study investigates the potential of utilizing the YouTube platform as a valuable data source for product review analysis—our research centers on Apple Inc. and its most profitable product, the Apple iPhone. Using user feedback from review videos, we employ a lexicon-based subjectivity analysis methodology to identify statements articulating subjective viewpoints about the iPhone product. Traditional sentiment analysis methods categorize opinionated views into two broad categories: positive or negative. To assess the general market perception of the product, we employ SpaCy’s aspect extraction functionality to identify significant parts of the product that are subject to viewer critique. A BERTopic model processes the user’s text by using topic modeling techniques to extract latent themes that provide insights into the various detected characteristics. The BERTopic model has high efficiency and yields a coherence score of 69%.

show abstract

Section: Youtubementioning

confidence: 99%

Subjectivity Analysis for Aspect-based Sentiment and Opinion Detection of YouTube Product Reviews

Tetteh,

Thushara

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…This facet provides businesses and organizations with invaluable insights into customer sentiments. Consequently, text analysis for emotion detection contributes significantly to better customer engagement [1][2][3][4] and facilitates product and service enhancements that align more closely with their needs. Beyond business applications, text analysis to emotion detection has a profound impact on assessing public opinion concerning significant events or issues [4], enabling a deeper understanding of how these events resonate with the public.…”

Section: Introductionmentioning

confidence: 99%

Detecting Emotional Sentiments in Textual Data Using Various Machine Learning and Deep Learning Techniques

Sallam,

Saif,

Rassem

et al. 2024

Preprint

View full text Add to dashboard Cite

The digital age has led to a significant increase in text data, including social media updates, articles, and text messages. The ability to understand and extract emotions from this data is crucial in fields such as customer service analysis, psychological research, and social studies. It allows businesses and organizations to gain insight into customer opinions and emotions, leading to better decision-making and alignment with customer needs. However, accurately detecting emotions from text poses challenges due to linguistic structures, cultural nuances, and contextual differences. Although artificial intelligence and text analysis models have made progress in addressing these challenges, there is still a need for more sophisticated methodologies to understand textual content and explore emotions. This study aims to employ a range of machine learning and deep learning methods, including logistic regression, Extra tree classifier, voting classifier, SGD, linearSVC, BiLSTM, BERT, RoBERTa, and DistilBERT, to detect emotions in textual content. The objective is to analyze and compare the outcomes of these methods. This involves extracting features and semantic relationships using techniques such as Word2Vec and FastText, and integrating them with features derived from TF-IDF, Bag of Words (BoW), and N-grams. The findings demonstrate the effectiveness of various models. Specifically, the SGD model utilizing N-grams and FastText achieved an accuracy of 88.42\% on the AIT-2018 dataset, while LinearSVC using N-grams and Word2Vec achieved an accuracy of 88.23\% on the ISEAR dataset. It is worth noting that the BERT transformer model outperformed others, achieving an accuracy of 93.67\% on the AIT-2018 dataset and 89.49\% on the ISEAR dataset. These results align with previous studies, further supporting their reliability and coherence.

show abstract

“…Research on YouTube comments in the Indian context is also gaining interest. A few examples are impoliteness strategies in comments (Kapoor, 2022), sentiments (Deori et al, 2021) and hope speech detection (Chakravarthi, 2022). Despite the growing digitization of Naga society, research on digital media and the Nagas is limited.…”

Section: Introductionmentioning

confidence: 99%

YouTube discourse of the Oting massacre in Nagaland: investigating affiliations, sentiments and Naga identity negotiation in YouTube comments

Muinao,

Ratnamala

2023

Media, War & Conflict

View full text Add to dashboard Cite

Personae identification and understanding the social bonds shared in online interactions are found to be key to combating misinformation and conspiratorial discourse as well as aiding in developing solutions for specific communities. The 2021 Oting massacre in Nagaland that killed 14 civilians sparked public outrage and widespread protests calling for justice and the repeal of the Armed Forces (Special Powers) Act in northeast India. The massacre received a lot of attention, including YouTube videos, and reignited discussion on militarization, Naga identity and a backlash over the botched operation. A close qualitative analysis of 500 randomly extracted comments from 10 selected YouTube videos identified 15 personae with unique linguistic patterns that reveal specific ideational targets and their affiliation strategies in the discourse. A sentiment analysis of 11,294 comments shows a higher negative score linked to condemnation, hate speech and conspiracy than a positive score linked to solidarity and empathy. ‘Nagaism’ as being a Naga is reimagined and reinforced via YouTube, countering misconceptions about Naga identity.

show abstract

Hope speech detection in YouTube comments

Cited by 21 publications

References 64 publications

Subjectivity Analysis for Aspect-based Sentiment and Opinion Detection of YouTube Product Reviews

Subjectivity Analysis for Aspect-based Sentiment and Opinion Detection of YouTube Product Reviews

Detecting Emotional Sentiments in Textual Data Using Various Machine Learning and Deep Learning Techniques

YouTube discourse of the Oting massacre in Nagaland: investigating affiliations, sentiments and Naga identity negotiation in YouTube comments

Contact Info

Product

Resources

About