Microblogs have become an important platform for people to publish,transform information and acquire knowledge.This paper focuses on the problem of discovering user interest in microblogs.In this paper,we propose a to...Microblogs have become an important platform for people to publish,transform information and acquire knowledge.This paper focuses on the problem of discovering user interest in microblogs.In this paper,we propose a topic mining model based on Latent Dirichlet Allocation(LDA) named user-topic model.For each user,the interests are divided into two parts by different ways to generate the microblogs:original interest and retweet interest.We represent a Gibbs sampling implementation for inference the parameters of our model,and discover not only user's original interest,but also retweet interest.Then we combine original interest and retweet interest to compute interest words for users.Experiments on a dataset of Sina microblogs demonstrate that our model is able to discover user interest effectively and outperforms existing topic models in this task.And we find that original interest and retweet interest are similar and the topics of interest contain user labels.The interest words discovered by our model reflect user labels,but range is much broader.展开更多
Digital twinning enables manufacturers to create digital representations of physical entities,thus implementing virtual simulations for product development.Previous efforts of digital twinning neglect the decisive con...Digital twinning enables manufacturers to create digital representations of physical entities,thus implementing virtual simulations for product development.Previous efforts of digital twinning neglect the decisive consumer feedback in product development stages,failing to cover the gap between physical and digital spaces.This work mines real-world consumer feedbacks through social media topics,which is significant to product development.We specifically analyze the prevalent time of a product topic,giving an insight into both consumer attention and the widely-discussed time of a product.The primary body of current studies regards the prevalent time prediction as an accompanying task or assumes the existence of a preset distribution.Therefore,these proposed solutions are either biased in focused objectives and underlying patterns or weak in the capability of generalization towards diverse topics.To this end,this work combines deep learning and survival analysis to predict the prevalent time of topics.We propose a specialized deep survival model which consists of two modules.The first module enriches input covariates by incorporating latent features of the time-varying text,and the second module fully captures the temporal pattern of a rumor by a recurrent network structure.Moreover,a specific loss function different from regular survival models is proposed to achieve a more reasonable prediction.Extensive experiments on real-world datasets demonstrate that our model significantly outperforms the state-of-the-art methods.展开更多
In the video captioning methods based on an encoder-decoder,limited visual features are extracted by an encoder,and a natural sentence of the video content is generated using a decoder.However,this kind ofmethod is de...In the video captioning methods based on an encoder-decoder,limited visual features are extracted by an encoder,and a natural sentence of the video content is generated using a decoder.However,this kind ofmethod is dependent on a single video input source and few visual labels,and there is a problem with semantic alignment between video contents and generated natural sentences,which are not suitable for accurately comprehending and describing the video contents.To address this issue,this paper proposes a video captioning method by semantic topic-guided generation.First,a 3D convolutional neural network is utilized to extract the spatiotemporal features of videos during the encoding.Then,the semantic topics of video data are extracted using the visual labels retrieved from similar video data.In the decoding,a decoder is constructed by combining a novel Enhance-TopK sampling algorithm with a Generative Pre-trained Transformer-2 deep neural network,which decreases the influence of“deviation”in the semantic mapping process between videos and texts by jointly decoding a baseline and semantic topics of video contents.During this process,the designed Enhance-TopK sampling algorithm can alleviate a long-tail problem by dynamically adjusting the probability distribution of the predicted words.Finally,the experiments are conducted on two publicly used Microsoft Research Video Description andMicrosoft Research-Video to Text datasets.The experimental results demonstrate that the proposed method outperforms several state-of-art approaches.Specifically,the performance indicators Bilingual Evaluation Understudy,Metric for Evaluation of Translation with Explicit Ordering,Recall Oriented Understudy for Gisting Evaluation-longest common subsequence,and Consensus-based Image Description Evaluation of the proposed method are improved by 1.2%,0.1%,0.3%,and 2.4% on the Microsoft Research Video Description dataset,and 0.1%,1.0%,0.1%,and 2.8% on the Microsoft Research-Video to Text dataset,respectively,compared with the existing video captioning methods.As a result,the proposed method can generate video captioning that is more closely aligned with human natural language expression habits.展开更多
Cataract is the main cause of visual impairment and blindness worldwide while the only effective cure for cataract is still surgery.Consecutive phacoemulsification under topical anesthesia has been the routine procedu...Cataract is the main cause of visual impairment and blindness worldwide while the only effective cure for cataract is still surgery.Consecutive phacoemulsification under topical anesthesia has been the routine procedure for cataract surgery.However,patients often grumbled that they felt more painful during the second-eye surgery compared to the first-eye surgery.The intraoperative pain experience has negative influence on satisfaction and willingness for second-eye cataract surgery of patients with bilateral cataracts.Intraoperative ocular pain is a complicated process induced by the nociceptors activation in the peripheral nervous system.Immunological,neuropsychological,and pharmacological factors work together in the enhancement of intraoperative pain.Accumulating published literatures have focused on the pain enhancement during the secondeye phacoemulsification surgeries.In this review,we searched PubMed database for articles associated with pain perception differences between consecutive cataract surgeries published up to Feb.1,2024.We summarized the recent research progress in mechanisms and interventions for pain perception enhancement in consecutive secondeye phacoemulsification cataract surgeries.This review aimed to provide novel insights into strategies for improving patients’intraoperative experience in second-eye cataract surgeries.展开更多
Modeling topics in short texts presents significant challenges due to feature sparsity, particularly when analyzing content generated by large-scale online users. This sparsity can substantially impair semantic captur...Modeling topics in short texts presents significant challenges due to feature sparsity, particularly when analyzing content generated by large-scale online users. This sparsity can substantially impair semantic capture accuracy. We propose a novel approach that incorporates pre-clustered knowledge into the BERTopic model while reducing the l2 norm for low-frequency words. Our method effectively mitigates feature sparsity during cluster mapping. Empirical evaluation on the StackOverflow dataset demonstrates that our approach outperforms baseline models, achieving superior Macro-F1 scores. These results validate the effectiveness of our proposed feature sparsity reduction technique for short-text topic modeling.展开更多
To improve the accuracy of text clustering, fuzzy c-means clustering based on topic concept sub-space (TCS2FCM) is introduced for classifying texts. Five evaluation functions are combined to extract key phrases. Con...To improve the accuracy of text clustering, fuzzy c-means clustering based on topic concept sub-space (TCS2FCM) is introduced for classifying texts. Five evaluation functions are combined to extract key phrases. Concept phrases, as well as the descriptions of final clusters, are presented using WordNet origin from key phrases. Initial centers and membership matrix are the most important factors affecting clustering performance. Orthogonal concept topic sub-spaces are built with the topic concept phrases representing topics of the texts and the initialization of centers and the membership matrix depend on the concept vectors in sub-spaces. The results show that, different from random initialization of traditional fuzzy c-means clustering, the initialization related to text content contributions can improve clustering precision.展开更多
Objective To investigate the effects of the topical use of aprotinin on thebasis of comprehensive blood conservations in cardiopulmonary bypass (CPB). Methods In a prospectiveclinical trial, 20 patients were randomly ...Objective To investigate the effects of the topical use of aprotinin on thebasis of comprehensive blood conservations in cardiopulmonary bypass (CPB). Methods In a prospectiveclinical trial, 20 patients were randomly divided into 2 groups. Control group: placebo was usedtopically. Aprotinin group: aprotinin was poured into the pericardial cavity before closure of thesternotomy. Before and 24h after surgery, hemoglobin (Hb), hematocrit (Hct), bleeding time (BT),clotting time (CT) and prothrombin time (PT) were measured. Meanwhile, amounts of the mediastinaldrainage and the hemoglobin loss were observed at 0, 2, 6 and 24h after operation. The samples fromthe mediastinal drainage were also collected to measure D-Dimer (D-D), tissue type plasminogenactivator (t-PA) activity, plasminogen activator inhibitor (PAI) activity and protein C (PC).Results In Aprotinin group, D-D, t-PA activity and PC were significantly reduced, compared withthose in Control group (P<0.05, P<0.05, P<0.01). On the contrary, PAI activity was significantlyincreased, compared with that in Control group. Amounts of the mediastinal drainage and thehemoglobin loss were decreased by 43% and 52%, compared with those in Control group. Conclusion Ourresults suggest that the topical use of aprotinin can have better effects on the basis ofcomprehensive moderate blood conservation.展开更多
University campus is the most important place for life, study, activity and experience of contemporary college students. It is helpful for students to survive and develop to create the topic space of campus. Taking th...University campus is the most important place for life, study, activity and experience of contemporary college students. It is helpful for students to survive and develop to create the topic space of campus. Taking the topic space of college campuses in Lishui City of Zhejiang Province as an example, the current situations are analyzed through questionnaire survey and field visit. The results show that uni- versity campus space needs a clear topic; the demands are generally large for the topics of exchange and communication, learning and thinking, sports and leisure in all kinds of space; the creation of these types of topic spaces should focus on the peaceful environment, beautiful scenery, privacy of the space and WlFI coverage.展开更多
English and Chinese belong to different language families,employing two distinct syntactic systems.English is subject-prominent,following the pattern of subject first,then predicate;while Chinese is topic-prominent,sh...English and Chinese belong to different language families,employing two distinct syntactic systems.English is subject-prominent,following the pattern of subject first,then predicate;while Chinese is topic-prominent,showing much flexibility in word arrangement as well as the necessity of subject and predicate.展开更多
Based on the interactive theory of reading, this study mainly explored the etlects ot topic familiarity and second language proficiency on IVA (Incidental Vocabulary Acquisition) of second language through reading. ...Based on the interactive theory of reading, this study mainly explored the etlects ot topic familiarity and second language proficiency on IVA (Incidental Vocabulary Acquisition) of second language through reading. By using two different measures (translation production and selection), this study found: (1) Vocabulary can be acquired incidentally in reading passages; (2) There are no significant interactive effects of topic familiarity and second language proficiency on vocabulary acquisition, but the two independent variables of topic familiarity and second language proficiency exerted their positively significant effect on incidental vocabulary acquisition, and (3) As for the two vocabulary measures, learners can acquire more words in translation selection than in translation production.展开更多
This paper explores how the Chinese college students' life is represented in some graffiti collected in campus.The article analyzes and compares the topics of graffiti from different settings and the linguistic fe...This paper explores how the Chinese college students' life is represented in some graffiti collected in campus.The article analyzes and compares the topics of graffiti from different settings and the linguistic features they manifest.The findings show that fewer graffiti from female toilet and classroom in this university pay attention to political issues compared with the graffiti abroad.Graffiti in female toilet mainly focus on the theme of love,and are found to be more interactive in discourse.Whereas graffiti on desks tend to cover mixed themes and be less interactive.There are more graphic graffiti and exam answers on the undergraduate students' desk than on the postgraduates'.Graffiti have some linguistic features as thematization,repetition and salience,etc.展开更多
基金This work was supported by the National High Technology Research and Development Program of China(No. 2010AA012505, 2011AA010702, 2012AA01A401 and 2012AA01A402), Chinese National Science Foundation (No. 60933005, 91124002,61303265), National Technology Support Foundation (No. 2012BAH38B04) and National 242 Foundation (No. 2011A010)
文摘Microblogs have become an important platform for people to publish,transform information and acquire knowledge.This paper focuses on the problem of discovering user interest in microblogs.In this paper,we propose a topic mining model based on Latent Dirichlet Allocation(LDA) named user-topic model.For each user,the interests are divided into two parts by different ways to generate the microblogs:original interest and retweet interest.We represent a Gibbs sampling implementation for inference the parameters of our model,and discover not only user's original interest,but also retweet interest.Then we combine original interest and retweet interest to compute interest words for users.Experiments on a dataset of Sina microblogs demonstrate that our model is able to discover user interest effectively and outperforms existing topic models in this task.And we find that original interest and retweet interest are similar and the topics of interest contain user labels.The interest words discovered by our model reflect user labels,but range is much broader.
基金supported by Sichuan Science and Technology Program(Nos.2019YFG0507,2020YFG0328 and 2021YFG0018)by National Natural Science Foundation of China(NSFC)under Grant No.U19A2059+1 种基金by the Young Scientists Fund of the National Natural Science Foundation of China under Grant No.61802050by the Fundamental Research Funds for the Central Universities(No.ZYGX2021J019).
文摘Digital twinning enables manufacturers to create digital representations of physical entities,thus implementing virtual simulations for product development.Previous efforts of digital twinning neglect the decisive consumer feedback in product development stages,failing to cover the gap between physical and digital spaces.This work mines real-world consumer feedbacks through social media topics,which is significant to product development.We specifically analyze the prevalent time of a product topic,giving an insight into both consumer attention and the widely-discussed time of a product.The primary body of current studies regards the prevalent time prediction as an accompanying task or assumes the existence of a preset distribution.Therefore,these proposed solutions are either biased in focused objectives and underlying patterns or weak in the capability of generalization towards diverse topics.To this end,this work combines deep learning and survival analysis to predict the prevalent time of topics.We propose a specialized deep survival model which consists of two modules.The first module enriches input covariates by incorporating latent features of the time-varying text,and the second module fully captures the temporal pattern of a rumor by a recurrent network structure.Moreover,a specific loss function different from regular survival models is proposed to achieve a more reasonable prediction.Extensive experiments on real-world datasets demonstrate that our model significantly outperforms the state-of-the-art methods.
基金supported in part by the National Natural Science Foundation of China under Grant 61873277in part by the Natural Science Basic Research Plan in Shaanxi Province of China underGrant 2020JQ-758in part by the Chinese Postdoctoral Science Foundation under Grant 2020M673446.
文摘In the video captioning methods based on an encoder-decoder,limited visual features are extracted by an encoder,and a natural sentence of the video content is generated using a decoder.However,this kind ofmethod is dependent on a single video input source and few visual labels,and there is a problem with semantic alignment between video contents and generated natural sentences,which are not suitable for accurately comprehending and describing the video contents.To address this issue,this paper proposes a video captioning method by semantic topic-guided generation.First,a 3D convolutional neural network is utilized to extract the spatiotemporal features of videos during the encoding.Then,the semantic topics of video data are extracted using the visual labels retrieved from similar video data.In the decoding,a decoder is constructed by combining a novel Enhance-TopK sampling algorithm with a Generative Pre-trained Transformer-2 deep neural network,which decreases the influence of“deviation”in the semantic mapping process between videos and texts by jointly decoding a baseline and semantic topics of video contents.During this process,the designed Enhance-TopK sampling algorithm can alleviate a long-tail problem by dynamically adjusting the probability distribution of the predicted words.Finally,the experiments are conducted on two publicly used Microsoft Research Video Description andMicrosoft Research-Video to Text datasets.The experimental results demonstrate that the proposed method outperforms several state-of-art approaches.Specifically,the performance indicators Bilingual Evaluation Understudy,Metric for Evaluation of Translation with Explicit Ordering,Recall Oriented Understudy for Gisting Evaluation-longest common subsequence,and Consensus-based Image Description Evaluation of the proposed method are improved by 1.2%,0.1%,0.3%,and 2.4% on the Microsoft Research Video Description dataset,and 0.1%,1.0%,0.1%,and 2.8% on the Microsoft Research-Video to Text dataset,respectively,compared with the existing video captioning methods.As a result,the proposed method can generate video captioning that is more closely aligned with human natural language expression habits.
基金Supported by the National Natural Science Foundation of China (No.82171038No.81974129)Jiangsu Provincial Medical Key Discipline (No.JSDW202245).
文摘Cataract is the main cause of visual impairment and blindness worldwide while the only effective cure for cataract is still surgery.Consecutive phacoemulsification under topical anesthesia has been the routine procedure for cataract surgery.However,patients often grumbled that they felt more painful during the second-eye surgery compared to the first-eye surgery.The intraoperative pain experience has negative influence on satisfaction and willingness for second-eye cataract surgery of patients with bilateral cataracts.Intraoperative ocular pain is a complicated process induced by the nociceptors activation in the peripheral nervous system.Immunological,neuropsychological,and pharmacological factors work together in the enhancement of intraoperative pain.Accumulating published literatures have focused on the pain enhancement during the secondeye phacoemulsification surgeries.In this review,we searched PubMed database for articles associated with pain perception differences between consecutive cataract surgeries published up to Feb.1,2024.We summarized the recent research progress in mechanisms and interventions for pain perception enhancement in consecutive secondeye phacoemulsification cataract surgeries.This review aimed to provide novel insights into strategies for improving patients’intraoperative experience in second-eye cataract surgeries.
文摘Modeling topics in short texts presents significant challenges due to feature sparsity, particularly when analyzing content generated by large-scale online users. This sparsity can substantially impair semantic capture accuracy. We propose a novel approach that incorporates pre-clustered knowledge into the BERTopic model while reducing the l2 norm for low-frequency words. Our method effectively mitigates feature sparsity during cluster mapping. Empirical evaluation on the StackOverflow dataset demonstrates that our approach outperforms baseline models, achieving superior Macro-F1 scores. These results validate the effectiveness of our proposed feature sparsity reduction technique for short-text topic modeling.
基金The National Natural Science Foundation of China(No60672056)Open Fund of MOE-MS Key Laboratory of Multime-dia Computing and Communication(No06120809)
文摘To improve the accuracy of text clustering, fuzzy c-means clustering based on topic concept sub-space (TCS2FCM) is introduced for classifying texts. Five evaluation functions are combined to extract key phrases. Concept phrases, as well as the descriptions of final clusters, are presented using WordNet origin from key phrases. Initial centers and membership matrix are the most important factors affecting clustering performance. Orthogonal concept topic sub-spaces are built with the topic concept phrases representing topics of the texts and the initialization of centers and the membership matrix depend on the concept vectors in sub-spaces. The results show that, different from random initialization of traditional fuzzy c-means clustering, the initialization related to text content contributions can improve clustering precision.
基金Supported by the Jiangsu Health Bureau Grand (B9606)
文摘Objective To investigate the effects of the topical use of aprotinin on thebasis of comprehensive blood conservations in cardiopulmonary bypass (CPB). Methods In a prospectiveclinical trial, 20 patients were randomly divided into 2 groups. Control group: placebo was usedtopically. Aprotinin group: aprotinin was poured into the pericardial cavity before closure of thesternotomy. Before and 24h after surgery, hemoglobin (Hb), hematocrit (Hct), bleeding time (BT),clotting time (CT) and prothrombin time (PT) were measured. Meanwhile, amounts of the mediastinaldrainage and the hemoglobin loss were observed at 0, 2, 6 and 24h after operation. The samples fromthe mediastinal drainage were also collected to measure D-Dimer (D-D), tissue type plasminogenactivator (t-PA) activity, plasminogen activator inhibitor (PAI) activity and protein C (PC).Results In Aprotinin group, D-D, t-PA activity and PC were significantly reduced, compared withthose in Control group (P<0.05, P<0.05, P<0.01). On the contrary, PAI activity was significantlyincreased, compared with that in Control group. Amounts of the mediastinal drainage and thehemoglobin loss were decreased by 43% and 52%, compared with those in Control group. Conclusion Ourresults suggest that the topical use of aprotinin can have better effects on the basis ofcomprehensive moderate blood conservation.
文摘University campus is the most important place for life, study, activity and experience of contemporary college students. It is helpful for students to survive and develop to create the topic space of campus. Taking the topic space of college campuses in Lishui City of Zhejiang Province as an example, the current situations are analyzed through questionnaire survey and field visit. The results show that uni- versity campus space needs a clear topic; the demands are generally large for the topics of exchange and communication, learning and thinking, sports and leisure in all kinds of space; the creation of these types of topic spaces should focus on the peaceful environment, beautiful scenery, privacy of the space and WlFI coverage.
文摘English and Chinese belong to different language families,employing two distinct syntactic systems.English is subject-prominent,following the pattern of subject first,then predicate;while Chinese is topic-prominent,showing much flexibility in word arrangement as well as the necessity of subject and predicate.
文摘Based on the interactive theory of reading, this study mainly explored the etlects ot topic familiarity and second language proficiency on IVA (Incidental Vocabulary Acquisition) of second language through reading. By using two different measures (translation production and selection), this study found: (1) Vocabulary can be acquired incidentally in reading passages; (2) There are no significant interactive effects of topic familiarity and second language proficiency on vocabulary acquisition, but the two independent variables of topic familiarity and second language proficiency exerted their positively significant effect on incidental vocabulary acquisition, and (3) As for the two vocabulary measures, learners can acquire more words in translation selection than in translation production.
文摘This paper explores how the Chinese college students' life is represented in some graffiti collected in campus.The article analyzes and compares the topics of graffiti from different settings and the linguistic features they manifest.The findings show that fewer graffiti from female toilet and classroom in this university pay attention to political issues compared with the graffiti abroad.Graffiti in female toilet mainly focus on the theme of love,and are found to be more interactive in discourse.Whereas graffiti on desks tend to cover mixed themes and be less interactive.There are more graphic graffiti and exam answers on the undergraduate students' desk than on the postgraduates'.Graffiti have some linguistic features as thematization,repetition and salience,etc.