In the age of information explosion and artificial intelligence, sentiment analysis tailored for the tobacco industry has emerged as a pivotal avenue for cigarette manufacturers to enhance their tobacco products. Exis...In the age of information explosion and artificial intelligence, sentiment analysis tailored for the tobacco industry has emerged as a pivotal avenue for cigarette manufacturers to enhance their tobacco products. Existing solutions have primarily focused on intrinsic features within consumer reviews and achieved significant progress through deep feature extraction models. However, they still face these two key limitations: (1) neglecting the influence of fundamental tobacco information on analyzing the sentiment inclination of consumer reviews, resulting in a lack of consistent sentiment assessment criteria across thousands of tobacco brands;(2) overlooking the syntactic dependencies between Chinese word phrases and the underlying impact of sentiment scores between word phrases on sentiment inclination determination. To tackle these challenges, we propose the External Knowledge-enhanced Cross-Attention Fusion model, CITSA. Specifically, in the Cross Infusion Layer, we fuse consumer comment information and tobacco fundamental information through interactive attention mechanisms. In the Textual Attention Enhancement Layer, we introduce an emotion-oriented syntactic dependency graph and incorporate sentiment-syntactic relationships into consumer comments through a graph convolution network module. Subsequently, the Textual Attention Layer is introduced to combine these two feature representations. Additionally, we compile a Chinese-oriented tobacco sentiment analysis dataset, comprising 55,096 consumer reviews and 2074 tobacco fundamental information entries. Experimental results on our self-constructed datasets consistently demonstrate that our proposed model outperforms state-of-the-art methods in terms of accuracy, precision, recall, and F1-score.展开更多
Emotion cause extraction(ECE)task that aims at extracting potential trigger events of certain emotions has attracted extensive attention recently.However,current work neglects the implicit emotion expressed without an...Emotion cause extraction(ECE)task that aims at extracting potential trigger events of certain emotions has attracted extensive attention recently.However,current work neglects the implicit emotion expressed without any explicit emotional keywords,which appears more frequently in application scenarios.The lack of explicit emotion information makes it extremely hard to extract emotion causes only with the local context.Moreover,an entire event is usually across multiple clauses,while existing work merely extracts cause events at clause level and cannot effectively capture complete cause event information.To address these issues,the events are first redefined at the tuple level and a span-based tuple-level algorithm is proposed to extract events from different clauses.Based on it,a corpus for implicit emotion cause extraction that tries to extract causes of implicit emotions is constructed.The authors propose a knowledge-enriched jointlearning model of implicit emotion recognition and implicit emotion cause extraction tasks(KJ-IECE),which leverages commonsense knowledge from ConceptNet and NRC_VAD to better capture connections between emotion and corresponding cause events.Experiments on both implicit and explicit emotion cause extraction datasets demonstrate the effectiveness of the proposed model.展开更多
The development of the Internet has provided firms with the ideal opportunity to make up for the knowledge gap for achieving internal knowledge generation(IKG)and external knowledge acquisition(EKA).It is worth explor...The development of the Internet has provided firms with the ideal opportunity to make up for the knowledge gap for achieving internal knowledge generation(IKG)and external knowledge acquisition(EKA).It is worth exploring how Internet resources can be used to satisfy organizational knowledge needs efficiently to adapt to dynamic environments.Thus,according to the resource-based view,knowledge-based view,and contingency theory,we study the impact of different types of Internet resources on the two modes of knowledge creation(IKG and EKA),as well as the moderating effect of environmental dynamism(ED)on this relationship.The hypothesized relationships were tested using the hierarchical regression analysis method with survey data collected from 399 Chinese firms.We found that Internet relationship resource and Internet human resource can simultaneously facilitate IKG and EKA,while Internet infrastructure resource positively affects IKG but has no significant impact on EKA.Furthermore,ED positively moderates the relationship between Internet relationship resource and IKG and EKA,but negatively moderates the relationship between Internet human resource and EKA.展开更多
This study aims to investigate the main factors driving technological innovation within firms in the manufacturing and service sectors of the Czech Republic.We apply a binary logistic regression model to cross-section...This study aims to investigate the main factors driving technological innovation within firms in the manufacturing and service sectors of the Czech Republic.We apply a binary logistic regression model to cross-sectional data from 502 firms,obtained from the World Bank Enterprise Survey.The results of our empirical investigation show that certain elements of the business environment,such as the tax rate,serve as significant obstacles to firms’product innovations.The results also confirm that international technological linkagesdmeasured by international quality certificates and foreign technology licensesdaffect technological innovations.Moreover,we found that internal R&D activities positively impact technological innovation across all sectors;contrarily,we found that process innovation in the manufacturing sector is positively influenced by foreign technology licenses and business association membership.Process innovations in the service sector are positively correlated with external R&D and financing from banking institutions.Finally,business association membership does not positively influence technological innovation in the service sector.Our findings have salient implications for firm managers,policymakers,and scholars aiming to explore and improve innovation outcomes in transitional economies.展开更多
Script event stream prediction is a task that predicts events based on a given context or script.Most existing methods predict one subsequent event,limiting the ability to make a longer inference about the future.More...Script event stream prediction is a task that predicts events based on a given context or script.Most existing methods predict one subsequent event,limiting the ability to make a longer inference about the future.Moreover,external knowledge has been proven to be beneficial for event prediction and used in many methods in the form of relations between events.However,these methods focus mainly on the continuity of actions while ignoring the other components of events.To tackle these issues,we propose a Multi-step Script Event Prediction(MuSEP)method that can make a longer inference according to the given events.We adopt reinforcement learning to implement the multi-step prediction by treating the process as a Markov chain and setting the reward considering both chain-level and event-level thus ensuring the overall quality of prediction results.Additionally,we learn the representations of events with external knowledge which could better understand events and their components.Experimental results on four datasets demonstrate that our method not only outperforms state-of-the-art methods on one-step prediction but is also capable of making multi-step prediction.展开更多
基金supported by the Global Research and Innovation Platform Fund for Scientific Big Data Transmission(Grant No.241711KYSB20180002)National Key Research and Development Project of China(Grant No.2019YFB1405801).
文摘In the age of information explosion and artificial intelligence, sentiment analysis tailored for the tobacco industry has emerged as a pivotal avenue for cigarette manufacturers to enhance their tobacco products. Existing solutions have primarily focused on intrinsic features within consumer reviews and achieved significant progress through deep feature extraction models. However, they still face these two key limitations: (1) neglecting the influence of fundamental tobacco information on analyzing the sentiment inclination of consumer reviews, resulting in a lack of consistent sentiment assessment criteria across thousands of tobacco brands;(2) overlooking the syntactic dependencies between Chinese word phrases and the underlying impact of sentiment scores between word phrases on sentiment inclination determination. To tackle these challenges, we propose the External Knowledge-enhanced Cross-Attention Fusion model, CITSA. Specifically, in the Cross Infusion Layer, we fuse consumer comment information and tobacco fundamental information through interactive attention mechanisms. In the Textual Attention Enhancement Layer, we introduce an emotion-oriented syntactic dependency graph and incorporate sentiment-syntactic relationships into consumer comments through a graph convolution network module. Subsequently, the Textual Attention Layer is introduced to combine these two feature representations. Additionally, we compile a Chinese-oriented tobacco sentiment analysis dataset, comprising 55,096 consumer reviews and 2074 tobacco fundamental information entries. Experimental results on our self-constructed datasets consistently demonstrate that our proposed model outperforms state-of-the-art methods in terms of accuracy, precision, recall, and F1-score.
基金National Natural Science Foundation of China,Grant/Award Numbers:61671064,61732005National Key Research&Development Program,Grant/Award Number:2018YFC0831700。
文摘Emotion cause extraction(ECE)task that aims at extracting potential trigger events of certain emotions has attracted extensive attention recently.However,current work neglects the implicit emotion expressed without any explicit emotional keywords,which appears more frequently in application scenarios.The lack of explicit emotion information makes it extremely hard to extract emotion causes only with the local context.Moreover,an entire event is usually across multiple clauses,while existing work merely extracts cause events at clause level and cannot effectively capture complete cause event information.To address these issues,the events are first redefined at the tuple level and a span-based tuple-level algorithm is proposed to extract events from different clauses.Based on it,a corpus for implicit emotion cause extraction that tries to extract causes of implicit emotions is constructed.The authors propose a knowledge-enriched jointlearning model of implicit emotion recognition and implicit emotion cause extraction tasks(KJ-IECE),which leverages commonsense knowledge from ConceptNet and NRC_VAD to better capture connections between emotion and corresponding cause events.Experiments on both implicit and explicit emotion cause extraction datasets demonstrate the effectiveness of the proposed model.
基金This work was supported by the National Social Science Foundation of China(No.15FGL005)the National Natural Science Foundation of China(Nos.71403052 and 71403055)the Social Science Planning Project of Fujian Province of China(No.FJ2016C030).
文摘The development of the Internet has provided firms with the ideal opportunity to make up for the knowledge gap for achieving internal knowledge generation(IKG)and external knowledge acquisition(EKA).It is worth exploring how Internet resources can be used to satisfy organizational knowledge needs efficiently to adapt to dynamic environments.Thus,according to the resource-based view,knowledge-based view,and contingency theory,we study the impact of different types of Internet resources on the two modes of knowledge creation(IKG and EKA),as well as the moderating effect of environmental dynamism(ED)on this relationship.The hypothesized relationships were tested using the hierarchical regression analysis method with survey data collected from 399 Chinese firms.We found that Internet relationship resource and Internet human resource can simultaneously facilitate IKG and EKA,while Internet infrastructure resource positively affects IKG but has no significant impact on EKA.Furthermore,ED positively moderates the relationship between Internet relationship resource and IKG and EKA,but negatively moderates the relationship between Internet human resource and EKA.
文摘This study aims to investigate the main factors driving technological innovation within firms in the manufacturing and service sectors of the Czech Republic.We apply a binary logistic regression model to cross-sectional data from 502 firms,obtained from the World Bank Enterprise Survey.The results of our empirical investigation show that certain elements of the business environment,such as the tax rate,serve as significant obstacles to firms’product innovations.The results also confirm that international technological linkagesdmeasured by international quality certificates and foreign technology licensesdaffect technological innovations.Moreover,we found that internal R&D activities positively impact technological innovation across all sectors;contrarily,we found that process innovation in the manufacturing sector is positively influenced by foreign technology licenses and business association membership.Process innovations in the service sector are positively correlated with external R&D and financing from banking institutions.Finally,business association membership does not positively influence technological innovation in the service sector.Our findings have salient implications for firm managers,policymakers,and scholars aiming to explore and improve innovation outcomes in transitional economies.
基金supported in part by the Project of the National Natural Science Foundation of China(Nos.62206166 and 61991410)Shanghai Sailing Program(No.23YF1413000)Shanghai Pujiang Program(No.22PJ1403800).
文摘Script event stream prediction is a task that predicts events based on a given context or script.Most existing methods predict one subsequent event,limiting the ability to make a longer inference about the future.Moreover,external knowledge has been proven to be beneficial for event prediction and used in many methods in the form of relations between events.However,these methods focus mainly on the continuity of actions while ignoring the other components of events.To tackle these issues,we propose a Multi-step Script Event Prediction(MuSEP)method that can make a longer inference according to the given events.We adopt reinforcement learning to implement the multi-step prediction by treating the process as a Markov chain and setting the reward considering both chain-level and event-level thus ensuring the overall quality of prediction results.Additionally,we learn the representations of events with external knowledge which could better understand events and their components.Experimental results on four datasets demonstrate that our method not only outperforms state-of-the-art methods on one-step prediction but is also capable of making multi-step prediction.
