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
There have never been more ways for us to ＂communicate＂ than what we may have today as we keep developing new technologies that allow us with alternative forms of interaction other than face-to-face conversation. Ou...There have never been more ways for us to ＂communicate＂ than what we may have today as we keep developing new technologies that allow us with alternative forms of interaction other than face-to-face conversation. Our age indeed distinguishes itself by its ever more rapid transformations in the kinds of mediation for such encounters. But, especially when they are new, technologies may deeply affect how we see the world, our communities, our relationships, and ourselves. For, as people usually respond to new media with much excitement as well as a big amount of confusion, and these media may conduct to social and cultural reorganization, they should as well incite more sober reflections about such changes before they become so taken for granted to appear as almost ＂invisible＂展开更多
Purpose： We propose and apply a simplified nowcasting model to understand the correlations between social attention and topic trends of scientific publications. Design/methodology/approach： First, topics are generat...Purpose： We propose and apply a simplified nowcasting model to understand the correlations between social attention and topic trends of scientific publications. Design/methodology/approach： First, topics are generated from the obesity corpus by using the latent Dirichlet allocation （LDA） algorithm and time series of keyword search trends in Google Trends are obtained. We then establish the structural time series model using data from January 2004 to December 2012, and evaluate the model using data from January 2013. We employ a state-space model to separate different non-regression components in an observational time series （i.e. the tendency and the seasonality） and apply the ＂spike and slab prior＂ and stepwise regression to analyze the correlations between the regression component and the social media attention. The two parts are combined using Markov-chain Monte Carlo sampling techniques to obtain our results. Findings： The results of our study show that （1） the number of publications on child obesity increases at a lower rate than that of diabetes publications; （2） the number of publication on a given topic may exhibit a relationship with the season or time of year; and （3） there exists a correlation between the number of publications on a given topic and its social media attention, i.e. the search frequency related to that topic as identified by Google Trends. We found that our model is also able to predict the number of publications related to a given topic.展开更多
INTRODUCTIONCrypt epithelial cells in normal small intestineproliferate at a high speed. But they are verydifficult to culture in vitro and passage stably. A lotof studies have been done[1-16]. Some domestic labsisola...INTRODUCTIONCrypt epithelial cells in normal small intestineproliferate at a high speed. But they are verydifficult to culture in vitro and passage stably. A lotof studies have been done[1-16]. Some domestic labsisolated and cultured crypt cells from embryonalintestines and aseptic animal intestine, but failed.We introduced normal rat epithelial cell line-IEC-6from the USA and its living condition for stablepassage was successfully established after trials. Thecell line was testified to be the small intestinalepithelial cell by electron microscopy,immunihistochemistry and enzymatic histoch-emistry. It has been applied to some relatedresearch work[17-21]. It was found that manyfactors were involved in the culture system. Ourpresent study focuses on the culture method and theinfluencing factors on IEC-6.展开更多
The extraction of entity relationship triples is very important to build a knowledge graph(KG),meanwhile,various entity relationship extraction algorithms are mostly based on data-driven,especially for the current pop...The extraction of entity relationship triples is very important to build a knowledge graph(KG),meanwhile,various entity relationship extraction algorithms are mostly based on data-driven,especially for the current popular deep learning algorithms.Therefore,obtaining a large number of accurate triples is the key to build a good KG as well as train a good entity relationship extraction algorithm.Because of business requirements,this KG’s application field is determined and the experts’opinions also must be satisfied.Considering these factors we adopt the top-down method which refers to determining the data schema firstly,then filling the specific data according to the schema.The design of data schema is the top-level design of KG,and determining the data schema according to the characteristics of KG is equivalent to determining the scope of data’s collection and the mode of data’s organization.This method is generally suitable for the construction of domain KG.This article proposes a fast and efficient method to extract the topdown type KG’s triples in social media with the help of structured data in the information box on the right side of the related encyclopedia webpage.At the same time,based on the obtained triples,a data labeling method is proposed to obtain sufficiently high-quality training data,using in various Natural Language Processing(NLP)information extraction algorithms’training.展开更多
Purpose:The article examines the role of digital and,in particular,social media in business-to-business marketing in the international software industry.The authors responded to calls for empirical research on how the...Purpose:The article examines the role of digital and,in particular,social media in business-to-business marketing in the international software industry.The authors responded to calls for empirical research on how these media impact buyer-vendor relationships and the conjunction of the marketing and sales processes,particularly the distribution of complex software solutions.This paper develops a digital framework and discusses the managerial consequences.Design/methodology/approach:The model arises by merging themes derived from literature,experts,and job descriptions.Mixed Methods included conducting semi-structured interviews across marketing,business development,and sales executives from buyers,vendors,and third parties of various industries,supplemented by a survey of 530+executives.Findings:Multinational companies secure competitive advantage through agile business processes to improve buyer-vendor relationships in the digital era.Digital media enable vendors to interact continuously with buyers,gather intelligence,and foster mutually beneficial,trustworthy,long-term relationships.The objective is to prompt transactions and secure revenue streams.Research limitations/implications:The outcomes of this research center on North America,Western Europe(including the UK),and DACH(Germany-Austria-Switzerland),affecting the generalizability.Originality/value:The research is novel and bridges several gaps concerning industrial relationships in digitalization:it merges buyer,vendor,and third-party’s perspectives on an international scale.It provides deeper insights into existing and new relationships by identifying relevant digital/social media platforms,the underlying usage motivation,and fundamental B2B processes.Finally,it equips practitioners with metrics to improve performance.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.
文摘There have never been more ways for us to ＂communicate＂ than what we may have today as we keep developing new technologies that allow us with alternative forms of interaction other than face-to-face conversation. Our age indeed distinguishes itself by its ever more rapid transformations in the kinds of mediation for such encounters. But, especially when they are new, technologies may deeply affect how we see the world, our communities, our relationships, and ourselves. For, as people usually respond to new media with much excitement as well as a big amount of confusion, and these media may conduct to social and cultural reorganization, they should as well incite more sober reflections about such changes before they become so taken for granted to appear as almost ＂invisible＂
基金supported by the National Research Foundation of Korea Grant funded by the Korean Government (NRF-2012-2012S1A3A2033291)the Yonsei University Future-leading Research Initiative of 2014
文摘Purpose： We propose and apply a simplified nowcasting model to understand the correlations between social attention and topic trends of scientific publications. Design/methodology/approach： First, topics are generated from the obesity corpus by using the latent Dirichlet allocation （LDA） algorithm and time series of keyword search trends in Google Trends are obtained. We then establish the structural time series model using data from January 2004 to December 2012, and evaluate the model using data from January 2013. We employ a state-space model to separate different non-regression components in an observational time series （i.e. the tendency and the seasonality） and apply the ＂spike and slab prior＂ and stepwise regression to analyze the correlations between the regression component and the social media attention. The two parts are combined using Markov-chain Monte Carlo sampling techniques to obtain our results. Findings： The results of our study show that （1） the number of publications on child obesity increases at a lower rate than that of diabetes publications; （2） the number of publication on a given topic may exhibit a relationship with the season or time of year; and （3） there exists a correlation between the number of publications on a given topic and its social media attention, i.e. the search frequency related to that topic as identified by Google Trends. We found that our model is also able to predict the number of publications related to a given topic.
基金Foundation ttem Project C. B. 10.00. GL. 03 at Idaho National LaboratoryAcknowledgements This work is supported by the laboratory directed research and development （LDRD） project C. B. 10.00. GL. 03 at Idaho National Laboratory （INL）, which is operated by the Battelle Energy Alliance for the U. S. Department of Energy.
基金Supported by the National Natural Science Foundation of China, No.39100119
文摘INTRODUCTIONCrypt epithelial cells in normal small intestineproliferate at a high speed. But they are verydifficult to culture in vitro and passage stably. A lotof studies have been done[1-16]. Some domestic labsisolated and cultured crypt cells from embryonalintestines and aseptic animal intestine, but failed.We introduced normal rat epithelial cell line-IEC-6from the USA and its living condition for stablepassage was successfully established after trials. Thecell line was testified to be the small intestinalepithelial cell by electron microscopy,immunihistochemistry and enzymatic histoch-emistry. It has been applied to some relatedresearch work[17-21]. It was found that manyfactors were involved in the culture system. Ourpresent study focuses on the culture method and theinfluencing factors on IEC-6.
文摘The extraction of entity relationship triples is very important to build a knowledge graph(KG),meanwhile,various entity relationship extraction algorithms are mostly based on data-driven,especially for the current popular deep learning algorithms.Therefore,obtaining a large number of accurate triples is the key to build a good KG as well as train a good entity relationship extraction algorithm.Because of business requirements,this KG’s application field is determined and the experts’opinions also must be satisfied.Considering these factors we adopt the top-down method which refers to determining the data schema firstly,then filling the specific data according to the schema.The design of data schema is the top-level design of KG,and determining the data schema according to the characteristics of KG is equivalent to determining the scope of data’s collection and the mode of data’s organization.This method is generally suitable for the construction of domain KG.This article proposes a fast and efficient method to extract the topdown type KG’s triples in social media with the help of structured data in the information box on the right side of the related encyclopedia webpage.At the same time,based on the obtained triples,a data labeling method is proposed to obtain sufficiently high-quality training data,using in various Natural Language Processing(NLP)information extraction algorithms’training.
文摘Purpose:The article examines the role of digital and,in particular,social media in business-to-business marketing in the international software industry.The authors responded to calls for empirical research on how these media impact buyer-vendor relationships and the conjunction of the marketing and sales processes,particularly the distribution of complex software solutions.This paper develops a digital framework and discusses the managerial consequences.Design/methodology/approach:The model arises by merging themes derived from literature,experts,and job descriptions.Mixed Methods included conducting semi-structured interviews across marketing,business development,and sales executives from buyers,vendors,and third parties of various industries,supplemented by a survey of 530+executives.Findings:Multinational companies secure competitive advantage through agile business processes to improve buyer-vendor relationships in the digital era.Digital media enable vendors to interact continuously with buyers,gather intelligence,and foster mutually beneficial,trustworthy,long-term relationships.The objective is to prompt transactions and secure revenue streams.Research limitations/implications:The outcomes of this research center on North America,Western Europe(including the UK),and DACH(Germany-Austria-Switzerland),affecting the generalizability.Originality/value:The research is novel and bridges several gaps concerning industrial relationships in digitalization:it merges buyer,vendor,and third-party’s perspectives on an international scale.It provides deeper insights into existing and new relationships by identifying relevant digital/social media platforms,the underlying usage motivation,and fundamental B2B processes.Finally,it equips practitioners with metrics to improve performance.
