Predicting information dissemination on social media,specifcally users’reposting behavior,is crucial for applications such as advertising campaigns.Conventional methods use deep neural networks to make predictions ba...Predicting information dissemination on social media,specifcally users’reposting behavior,is crucial for applications such as advertising campaigns.Conventional methods use deep neural networks to make predictions based on features related to user topic interests and social preferences.However,these models frequently fail to account for the difculties arising from limited training data and model size,which restrict their capacity to learn and capture the intricate patterns within microblogging data.To overcome this limitation,we introduce a novel model Adapt pre-trained Large Language model for Reposting Prediction(ALL-RP),which incorporates two key steps:(1)extracting features from post content and social interactions using a large language model with extensive parameters and trained on a vast corpus,and(2)performing semantic and temporal adaptation to transfer the large language model’s knowledge of natural language,vision,and graph structures to reposting prediction tasks.Specifcally,the temporal adapter in the ALL-RP model captures multi-dimensional temporal information from evolving patterns of user topic interests and social preferences,thereby providing a more realistic refection of user attributes.Additionally,to enhance the robustness of feature modeling,we introduce a variant of the temporal adapter that implements multiple temporal adaptations in parallel while maintaining structural simplicity.Experimental results on real-world datasets demonstrate that the ALL-RP model surpasses state-of-the-art models in predicting both individual user reposting behavior and group sharing behavior,with performance gains of 2.81%and 4.29%,respectively.展开更多
Microblogging platforms like X(formerly Twitter)and Sina Weibo have become key channels for spreading information online.Accurately predicting information spread,such as users’reposting activities,is essential for ap...Microblogging platforms like X(formerly Twitter)and Sina Weibo have become key channels for spreading information online.Accurately predicting information spread,such as users’reposting activities,is essential for applications including content recommendation and analyzing public sentiment.Current advanced models rely on deep representation learning to extract features from various inputs,such as users’social connections and repost history,to forecast reposting behavior.Nonetheless,these models frequently ignore intrinsic confounding factors,which may cause the models to capture spurious relationships,ultimately impacting prediction performance.To address this limitation,we propose a novel Debiased Reposting Prediction model(DRP).Our model mitigates the influence of confounding variables by incorporating intervention operations from causal inference,enabling it to learn the causal associations between features and user reposting behavior.Specifically,we introduce a memory network within DRP to enhance the model’s perception of confounder distributions.This network aggregates and learns confounding information dispersed across different training data batches by optimizing the reconstruction loss.Furthermore,recognizing the challenge of acquiring prior knowledge of causal graphs,which is crucial for causal inference,we develop a causal discovery module within DRP(CD-DRP).This module allows the model to autonomously uncover the causal graph of feature variables by analyzing microblogging data.Experimental results on multiple real-world datasets demonstrate that our proposed method effectively uncovers causal relationships between variables,exhibits strong time efficiency,and outperforms state-of-the-art models in prediction performance(improved by 2.54%)and overfitting reduction(by 7.44%).展开更多
This study uses the Elaboration Likelihood Model （ELM） and social presence theory to examine the microblogging reposting mechanism. Subjective and objective data were collected from 216 respondents in a field experi...This study uses the Elaboration Likelihood Model （ELM） and social presence theory to examine the microblogging reposting mechanism. Subjective and objective data were collected from 216 respondents in a field experiment. The results indicate that information quality and source credibility of microblogging messages affect users＇ reposting intention by affecting their perceptions of the usefulness and enjoyment of the information. Perceived enjoyment has a greater impact on reposting intention than perceived usefulness. Furthermore, users are able to perceive social presence when interacting with microblogging messages. Social presence plays a full mediating role between information quality and perceived enjoyment, and a partial mediating role between information quality and perceived usefulness.展开更多
Advertorials have been shown to influence advertising recall and brand evaluation. However, no research has examined their impact on sales. This study uses longitudinal data on durable consumer goods in China to asses...Advertorials have been shown to influence advertising recall and brand evaluation. However, no research has examined their impact on sales. This study uses longitudinal data on durable consumer goods in China to assess the extent to which advertorials influence sales. The study finds that advertorials have dual, positive effects on firms＇ sales： a direct effect through original copy and a reposting effect through online exposure.展开更多
文摘Predicting information dissemination on social media,specifcally users’reposting behavior,is crucial for applications such as advertising campaigns.Conventional methods use deep neural networks to make predictions based on features related to user topic interests and social preferences.However,these models frequently fail to account for the difculties arising from limited training data and model size,which restrict their capacity to learn and capture the intricate patterns within microblogging data.To overcome this limitation,we introduce a novel model Adapt pre-trained Large Language model for Reposting Prediction(ALL-RP),which incorporates two key steps:(1)extracting features from post content and social interactions using a large language model with extensive parameters and trained on a vast corpus,and(2)performing semantic and temporal adaptation to transfer the large language model’s knowledge of natural language,vision,and graph structures to reposting prediction tasks.Specifcally,the temporal adapter in the ALL-RP model captures multi-dimensional temporal information from evolving patterns of user topic interests and social preferences,thereby providing a more realistic refection of user attributes.Additionally,to enhance the robustness of feature modeling,we introduce a variant of the temporal adapter that implements multiple temporal adaptations in parallel while maintaining structural simplicity.Experimental results on real-world datasets demonstrate that the ALL-RP model surpasses state-of-the-art models in predicting both individual user reposting behavior and group sharing behavior,with performance gains of 2.81%and 4.29%,respectively.
文摘Microblogging platforms like X(formerly Twitter)and Sina Weibo have become key channels for spreading information online.Accurately predicting information spread,such as users’reposting activities,is essential for applications including content recommendation and analyzing public sentiment.Current advanced models rely on deep representation learning to extract features from various inputs,such as users’social connections and repost history,to forecast reposting behavior.Nonetheless,these models frequently ignore intrinsic confounding factors,which may cause the models to capture spurious relationships,ultimately impacting prediction performance.To address this limitation,we propose a novel Debiased Reposting Prediction model(DRP).Our model mitigates the influence of confounding variables by incorporating intervention operations from causal inference,enabling it to learn the causal associations between features and user reposting behavior.Specifically,we introduce a memory network within DRP to enhance the model’s perception of confounder distributions.This network aggregates and learns confounding information dispersed across different training data batches by optimizing the reconstruction loss.Furthermore,recognizing the challenge of acquiring prior knowledge of causal graphs,which is crucial for causal inference,we develop a causal discovery module within DRP(CD-DRP).This module allows the model to autonomously uncover the causal graph of feature variables by analyzing microblogging data.Experimental results on multiple real-world datasets demonstrate that our proposed method effectively uncovers causal relationships between variables,exhibits strong time efficiency,and outperforms state-of-the-art models in prediction performance(improved by 2.54%)and overfitting reduction(by 7.44%).
基金supported by the National Natural Science Foundation of China (No. 71272028)the MOE Project of Key Research Institute of Humanity and Social Sciences at Universities (No. 13JJD630008)
文摘This study uses the Elaboration Likelihood Model （ELM） and social presence theory to examine the microblogging reposting mechanism. Subjective and objective data were collected from 216 respondents in a field experiment. The results indicate that information quality and source credibility of microblogging messages affect users＇ reposting intention by affecting their perceptions of the usefulness and enjoyment of the information. Perceived enjoyment has a greater impact on reposting intention than perceived usefulness. Furthermore, users are able to perceive social presence when interacting with microblogging messages. Social presence plays a full mediating role between information quality and perceived enjoyment, and a partial mediating role between information quality and perceived usefulness.
文摘Advertorials have been shown to influence advertising recall and brand evaluation. However, no research has examined their impact on sales. This study uses longitudinal data on durable consumer goods in China to assess the extent to which advertorials influence sales. The study finds that advertorials have dual, positive effects on firms＇ sales： a direct effect through original copy and a reposting effect through online exposure.
