Suicide has become a critical concern,necessitating the development of effective preventative strategies.Social media platforms offer a valuable resource for identifying signs of suicidal ideation.Despite progress in ...Suicide has become a critical concern,necessitating the development of effective preventative strategies.Social media platforms offer a valuable resource for identifying signs of suicidal ideation.Despite progress in detecting suicidal ideation on social media,accurately identifying individuals who express suicidal thoughts less openly or infrequently poses a significant challenge.To tackle this,we have developed a dataset focused on Chinese suicide narratives from Weibo’s Tree Hole feature and introduced an ensemble model named Text Convolutional Neural Network based on Social Network relationships(TCNN-SN).This model enhances predictive performance by leveraging social network relationship features and applying correction factors within a weighted linear fusion framework.It is specifically designed to identify key individuals who can help uncover hidden suicidal users and clusters.Our model,assessed using the bespoke dataset and benchmarked against alternative classification approaches,demonstrates superior accuracy,F1-score and AUC metrics,achieving 88.57%,88.75%and 94.25%,respectively,outperforming traditional TextCNN models by 12.18%,10.84%and 10.85%.We assert that our methodology offers a significant advancement in the predictive identification of individuals at risk,thereby contributing to the prevention and reduction of suicide incidences.展开更多
BACKGROUND Gut microbiota is an emerging field of research,with related research having breakthrough development in the past 15 years.Bibliometric analysis can be applied to analyze the evolutionary trends and emergin...BACKGROUND Gut microbiota is an emerging field of research,with related research having breakthrough development in the past 15 years.Bibliometric analysis can be applied to analyze the evolutionary trends and emerging hotspots in this field.AIM To study the subject trends and knowledge structures of gut microbiota related research fields from 2004 to 2018.METHODS The literature data on gut microbiota were identified and downloaded from the PubMed database.Through biclustering analysis,strategic diagrams,and social network analysis diagrams,the main trend and knowledge structure of research fields concerning gut microbiota were analyzed to obtain and compare the research hotspots in each period.RESULTS According to the strategic coordinates and social relationship network map,Clostridium Infections/microbiology,Clostridium Infections/therapy,RNA,Ribosomal,16S/genetics,Microbiota/genetics,Microbiota/immunology,Dysbiosis/immunology,Infla-mmation/immunology,Fecal Microbiota Transplantation/methods,Fecal Microbiota Transplantation can be used as an emerging research hotspot in the past 5 years(2014-2018).CONCLUSION Some subjects were not yet fully studied according to the strategic coordinates;and the emerging hotspots in the social network map can be considered as directions of future research.展开更多
基金funded by Outstanding Youth Team Project of Central Universities(QNTD202308).
文摘Suicide has become a critical concern,necessitating the development of effective preventative strategies.Social media platforms offer a valuable resource for identifying signs of suicidal ideation.Despite progress in detecting suicidal ideation on social media,accurately identifying individuals who express suicidal thoughts less openly or infrequently poses a significant challenge.To tackle this,we have developed a dataset focused on Chinese suicide narratives from Weibo’s Tree Hole feature and introduced an ensemble model named Text Convolutional Neural Network based on Social Network relationships(TCNN-SN).This model enhances predictive performance by leveraging social network relationship features and applying correction factors within a weighted linear fusion framework.It is specifically designed to identify key individuals who can help uncover hidden suicidal users and clusters.Our model,assessed using the bespoke dataset and benchmarked against alternative classification approaches,demonstrates superior accuracy,F1-score and AUC metrics,achieving 88.57%,88.75%and 94.25%,respectively,outperforming traditional TextCNN models by 12.18%,10.84%and 10.85%.We assert that our methodology offers a significant advancement in the predictive identification of individuals at risk,thereby contributing to the prevention and reduction of suicide incidences.
基金Supported by the Liaoning Provincial Key R and D Guidance Plan Project in 2018,No.2018225009the Liaoning Colleges and Universities Basic Research Project,No.LFWK201710.
文摘BACKGROUND Gut microbiota is an emerging field of research,with related research having breakthrough development in the past 15 years.Bibliometric analysis can be applied to analyze the evolutionary trends and emerging hotspots in this field.AIM To study the subject trends and knowledge structures of gut microbiota related research fields from 2004 to 2018.METHODS The literature data on gut microbiota were identified and downloaded from the PubMed database.Through biclustering analysis,strategic diagrams,and social network analysis diagrams,the main trend and knowledge structure of research fields concerning gut microbiota were analyzed to obtain and compare the research hotspots in each period.RESULTS According to the strategic coordinates and social relationship network map,Clostridium Infections/microbiology,Clostridium Infections/therapy,RNA,Ribosomal,16S/genetics,Microbiota/genetics,Microbiota/immunology,Dysbiosis/immunology,Infla-mmation/immunology,Fecal Microbiota Transplantation/methods,Fecal Microbiota Transplantation can be used as an emerging research hotspot in the past 5 years(2014-2018).CONCLUSION Some subjects were not yet fully studied according to the strategic coordinates;and the emerging hotspots in the social network map can be considered as directions of future research.
