Incorporating Time Perspectives into Detection of Suicidal Ideation DOI
Qianyi Yang, Jing Zhou

Published: Aug. 28, 2023

As a vital risk to the public heath, suicide has been hot topic for related research. Time perspectives (TPs) have attracted increasing attention in recent years that making use of TPs can help gain insights into real motives behind ideation. take consideration how people think or appraise their past, present, future life would shape behavior. Conventional TP-oriented studies on tendency detection tend rely questionnaire surveys identify thoughts attempts. Such efforts suffer from weaknesses including low data collection efficiency and self-report bias. We proposed TP-enhanced deep multitask model, TP-GloVe-GRU, which TP is regarded as synergy both time emotions. The model performance was evaluated against CEASE dataset using range metrics. Results show incorporating ideation leads better most cases with an increase 2.27% accuracy assessment.

Language: Английский

Artificial intelligence and multimodal data fusion for smart healthcare: topic modeling and bibliometrics DOI Creative Commons
Xieling Chen, Haoran Xie, Xiaohui Tao

et al.

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(4)

Published: March 15, 2024

Abstract Advancements in artificial intelligence (AI) have driven extensive research into developing diverse multimodal data analysis approaches for smart healthcare. There is a scarcity of large-scale literature this field based on quantitative approaches. This study performed bibliometric and topic modeling examination 683 articles from 2002 to 2022, focusing topics trends, journals, countries/regions, institutions, authors, scientific collaborations. Results showed that, firstly, the number has grown 1 220 with majority being published interdisciplinary journals that link healthcare medical information technology AI. Secondly, significant rise quantity can be attributed increasing contribution scholars non-English speaking countries/regions noteworthy contributions made by authors USA India. Thirdly, researchers show high interest issues, especially, cross-modality magnetic resonance imaging (MRI) brain tumor analysis, cancer prognosis through multi-dimensional AI-assisted diagnostics personalization healthcare, each experiencing increase interest. an emerging trend towards issues such as applying generative adversarial networks contrastive learning image fusion synthesis utilizing combined spatiotemporal resolution functional MRI electroencephalogram data-centric manner. valuable enhancing researchers’ practitioners’ understanding present focal points upcoming trajectories AI-powered analysis.

Language: Английский

Citations

23
Towards sentiment and Temporal Aided Stance Detection of climate change tweets DOI
Apoorva Upadhyaya, Marco Fisichella, Wolfgang Nejdl

et al.

Information Processing & Management, Journal Year: 2023, Volume and Issue: 60(4), P. 103325 - 103325

Published: March 29, 2023

Language: Английский

Citations

19
CARES: CAuse Recognition for Emotion in Suicide Notes DOI
Soumitra Ghosh, Swarup Roy, Asif Ekbal

et al.

Lecture notes in computer science, Journal Year: 2022, Volume and Issue: unknown, P. 128 - 136

Published: Jan. 1, 2022

Language: Английский

Citations

17
VAD-assisted multitask transformer framework for emotion recognition and intensity prediction on suicide notes DOI
Soumitra Ghosh, Asif Ekbal, Pushpak Bhattacharyya

et al.

Information Processing & Management, Journal Year: 2022, Volume and Issue: 60(2), P. 103234 - 103234

Published: Dec. 16, 2022

Language: Английский

Citations

8
Predicting multi-label emojis, emotions, and sentiments in code-mixed texts using an emojifying sentiments framework DOI Creative Commons
Gopendra Vikram Singh, Soumitra Ghosh, Mauajama Firdaus

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: May 28, 2024

In the era of social media, use emojis and code-mixed language has become essential in online communication. However, selecting appropriate emoji that matches a particular sentiment or emotion text can be difficult. This paper presents novel task predicting multiple English-Hindi sentences proposes new dataset called SENTIMOJI, which extends SemEval 2020 Task 9 SentiMix dataset. Our approach is based on exploiting relationship between emotion, sentiment, to build an end-to-end framework. We replace self-attention sublayers transformer encoder with simple linear transformations RMS-layer norm instead normal layer norm. Moreover, we employ Gated Linear Unit Fully Connected layers predict identify tweet. experimental results SENTIMOJI demonstrate proposed multi-task framework outperforms single-task also show are strongly linked identifying aid accurately most suitable emoji. work contributes field natural processing help development more effective tools for analysis recognition languages. The codes data will available at https://www.iitp.ac.in/~ai-nlp-ml/resources.html#SENTIMOJI facilitate research.

Language: Английский

Citations

1
A Review on Emotion Detection from Text: Opportunities and Challenges DOI
Azra Mahmud,

Md. Mubtasim Fuad,

Muhammad Zulkifl Hasan

et al.

Lecture notes in networks and systems, Journal Year: 2024, Volume and Issue: unknown, P. 17 - 31

Published: Oct. 16, 2024

Language: Английский

Citations

0
Incorporating Time Perspectives into Detection of Suicidal Ideation DOI
Qianyi Yang, Jing Zhou

Published: Aug. 28, 2023

As a vital risk to the public heath, suicide has been hot topic for related research. Time perspectives (TPs) have attracted increasing attention in recent years that making use of TPs can help gain insights into real motives behind ideation. take consideration how people think or appraise their past, present, future life would shape behavior. Conventional TP-oriented studies on tendency detection tend rely questionnaire surveys identify thoughts attempts. Such efforts suffer from weaknesses including low data collection efficiency and self-report bias. We proposed TP-enhanced deep multitask model, TP-GloVe-GRU, which TP is regarded as synergy both time emotions. The model performance was evaluated against CEASE dataset using range metrics. Results show incorporating ideation leads better most cases with an increase 2.27% accuracy assessment.

Language: Английский

Citations

1