國立高雄大學圖資館 |

登入

回首頁

Transfer learning for harmful content detection

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Transfer learning for harmful content detection by Salar Mohtaj.
作者:	Mohtaj, Salar.
出版者:	Cham :Springer Nature Switzerland :2025.
面頁冊數:	xvi, 105 p. :ill., digital ;24 cm.
Contained By:	Springer Nature eBook
標題:	Transfer learning (Machine learning)
電子資源:	https://doi.org/10.1007/978-3-032-00850-3
ISBN:	9783032008503$q(electronic bk.)

Transfer learning for harmful content detection
Mohtaj, Salar.

Transfer learning for harmful content detection [electronic resource] /by Salar Mohtaj. - Cham :Springer Nature Switzerland :2025. - xvi, 105 p. :ill., digital ;24 cm. - T-Labs series in telecommunication services,2192-2829. - T-Labs series in telecommunication services..

Introduction -- Background -- The Impact of Pre-processing on Fake News Detection -- Transfer Learning for Harmful Content Detection -- Sentiment Analysis and Fake News Detection -- Outlook -- Conclusion.

This book provides an in-depth exploration of the effectiveness of transfer learning approaches in detecting deceptive content (i.e., fake news) and inappropriate content (i.e., hate speech). The author first addresses the issue of insufficient labeled data by reusing knowledge gained from other natural language processing (NLP) tasks, such as language modeling. He goes on to observe the connection between harmful content and emotional signals in text after emotional cues were integrated into the classification models to evaluate their impact on model performance. Additionally, since pre-processing plays an essential role in NLP tasks by enriching raw data-especially critical for tasks with limited data, such as fake news detection-the book analyzes various pre-processing strategies in a transfer learning context to enhance the detection of fake stories online. Optimal settings for transferring knowledge from pre-trained models across subtasks, including claim extraction and check-worthiness assessment, are also investigated. The author shows that the findings indicate that incorporating these features into check-worthy claim models can improve overall model performance, though integrating emotional signals did not significantly affect classifier results. Finally, the experiments highlight the importance of pre-processing for enhancing input text, particularly in social media contexts where content is often ambiguous and lacks context, leading to notable performance improvements. Explores the effectiveness of transfer learning approaches in detecting deceptive and inappropriate content; Analyzes pre-processing strategies in a transfer learning context to enhance the detection of fake stories online; Investigates optimal settings for transferring knowledge from pre-trained models across subtasks.

ISBN: 9783032008503$q(electronic bk.)

Standard No.: 10.1007/978-3-032-00850-3doiSubjects--Topical Terms:

949877
Transfer learning (Machine learning)

LC Class. No.: Q325.787 / .M66 2025

Dewey Class. No.: 006.31

Transfer learning for harmful content detection
LDR:03120nmm a2200361 a 4500 001 688579
003 DE-He213
005 20250926130549.0
006 m d
007 cr nn 008maaau
008 260318s2025 sz s 0 eng d
020 $a 9783032008503$q(electronic bk.)
020 $a 9783032008497$q(paper)
024 7 $a 10.1007/978-3-032-00850-3 $2 doi
035 $a 978-3-032-00850-3
040 $a GP $c GP
041 0 $a eng
050 4 $a Q325.787 $b .M66 2025
072 7 $a TJF $2 bicssc
072 7 $a UYS $2 bicssc
072 7 $a TEC067000 $2 bisacsh
072 7 $a TJF $2 thema
072 7 $a UYS $2 thema
082 0 4 $a 006.31 $2 23
090 $a Q325.787 $b .M699 2025
100 1 $a Mohtaj, Salar. $3 1003746
245 1 0 $a Transfer learning for harmful content detection $h [electronic resource] / $c by Salar Mohtaj.
260 $a Cham : $b Springer Nature Switzerland : $b Imprint: Springer, $c 2025.
300 $a xvi, 105 p. : $b ill., digital ; $c 24 cm.
490 1 $a T-Labs series in telecommunication services, $x 2192-2829
505 0 $a Introduction -- Background -- The Impact of Pre-processing on Fake News Detection -- Transfer Learning for Harmful Content Detection -- Sentiment Analysis and Fake News Detection -- Outlook -- Conclusion.
520 $a This book provides an in-depth exploration of the effectiveness of transfer learning approaches in detecting deceptive content (i.e., fake news) and inappropriate content (i.e., hate speech). The author first addresses the issue of insufficient labeled data by reusing knowledge gained from other natural language processing (NLP) tasks, such as language modeling. He goes on to observe the connection between harmful content and emotional signals in text after emotional cues were integrated into the classification models to evaluate their impact on model performance. Additionally, since pre-processing plays an essential role in NLP tasks by enriching raw data-especially critical for tasks with limited data, such as fake news detection-the book analyzes various pre-processing strategies in a transfer learning context to enhance the detection of fake stories online. Optimal settings for transferring knowledge from pre-trained models across subtasks, including claim extraction and check-worthiness assessment, are also investigated. The author shows that the findings indicate that incorporating these features into check-worthy claim models can improve overall model performance, though integrating emotional signals did not significantly affect classifier results. Finally, the experiments highlight the importance of pre-processing for enhancing input text, particularly in social media contexts where content is often ambiguous and lacks context, leading to notable performance improvements. Explores the effectiveness of transfer learning approaches in detecting deceptive and inappropriate content; Analyzes pre-processing strategies in a transfer learning context to enhance the detection of fake stories online; Investigates optimal settings for transferring knowledge from pre-trained models across subtasks.
650 0 $a Transfer learning (Machine learning) $3 949877
650 0 $a Disinformation. $3 860237
650 0 $a Online hate speech. $3 774237
650 0 $a Internet $x Safety measures. $3 293900
650 0 $a Internet $x Security measures. $3 192260
650 1 4 $a Signal, Speech and Image Processing. $3 919570
650 2 4 $a Natural Language Processing (NLP). $3 988974
650 2 4 $a Artificial Intelligence. $3 212515
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
830 0 $a T-Labs series in telecommunication services. $3 559885
856 4 0 $u https://doi.org/10.1007/978-3-032-00850-3
950 $a Engineering (SpringerNature-11647)