Hierarchical attention neural network for information cascade prediction

Zhong, Chu; Xiong, Fei; Pan, Shirui; Wang, Liang; Xiong, Xiaozhen

doi:10.1016/j.ins.2022.11.163

Cited by 30 publications

(10 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Online activities and usage intensity are responsible for the accumulation of online social capital [33,[53][54][55][56][57][58][59]. A positive and significant relationship between SNS intensity and online social capital has been reported in several studies that involved Facebook [2,17,32,36,50].…”

Section: Research Hypothesesmentioning

confidence: 97%

Intensity of SNS Use as a Predictor of Online Social Capital and the Moderating Role of SNS Platforms: An Empirical Study Using Partial Least Squares Structural Equation Modelling

et al. 2023

View full text Add to dashboard Cite

This study firstly aims to understand how social networking site usage results in online social capital formation, considering two different types of social networking sites (SNS)—LinkedIn and Facebook. It further aims to investigate if the process varies among different social networking sites or remains uniform. This study also validates two prominent scales, namely the Facebook Intensity Scale (FIS) and the Internet Social Capital Scale (ISCS). A structured questionnaire was administered through various social media platforms resulting in a total of 329 valid responses (167 LinkedIn users and 162 Facebook users). Applying the partial least squares method of structural equation modelling, it was found that social networking site use results in the formation of both online-bonding and online-bridging social capital for both types of SNS. Further, moderation analysis results show that the type of SNS platform does not affect the relationship between SNS intensity and online social capital. This implies that users’ social capitals are dependent on how they use an SNS. These findings have both practical and academic implications. They provide new insights into the usage, intensity, and online social capital that should be beneficial for commercial purposes. In terms of academic contribution, this research contributes to the scarce studies that have considered SNSs other than Facebook and also compared two SNSs. It further confirms the social capital theory in the field of online networking.

show abstract

Section: Research Hypothesesmentioning

confidence: 97%

Intensity of SNS Use as a Predictor of Online Social Capital and the Moderating Role of SNS Platforms: An Empirical Study Using Partial Least Squares Structural Equation Modelling

et al. 2023

View full text Add to dashboard Cite

show abstract

“…A related study [17] on topological recommendations employed user influence in social networks and their rating data to enhance personalized recommendations. A more advanced related study [34] deployed a hierarchical attention network, considering user influence and community redundancy, to improve cascade prediction in online platforms.…”

Section: Related Workmentioning

confidence: 99%

BERT4Loc: BERT for Location—POI Recommender System

2023

View full text Add to dashboard Cite

Recommending points of interest (POI) is a challenging task that requires extracting comprehensive location data from location-based social media platforms. To provide effective location-based recommendations, it is important to analyze users’ historical behavior and preferences. In this study, we present a sophisticated location-aware recommendation system that uses Bidirectional Encoder Representations from Transformers (BERT) to offer personalized location-based suggestions. Our model combines location information and user preferences to provide more relevant recommendations compared to models that predict the next POI in a sequence. Based on our experiments conducted on two benchmark datasets, we have observed that our BERT-based model surpasses baselines models in terms of HR by a significant margin of 6% compared to the second-best performing baseline. Furthermore, our model demonstrates a percentage gain of 1–2% in the NDCG compared to second best baseline. These results indicate the superior performance and effectiveness of our BERT-based approach in comparison to other models when evaluating HR and NDCG metrics. Moreover, we see the effectiveness of the proposed model for quality through additional experiments.

show abstract

“…For the convenience of research, the bidirectional link in the communication network, i.e., the undirected edges in the network, is transformed into two directed edges with opposite directions, thus transforming the hybrid weighted network into a directed-weighted network with only directed edges. The weights of communication links represent the flow of information transmitted between nodes, so the principle of similar weights is used [23], i.e., the larger the weight, the stronger the connection between nodes. On this basis, the nodes in the network can then be studied using a directedweighted network node importance assessment method.…”

Section: Communication Network and Its Node Importance 21 Communicati...mentioning

confidence: 99%

Hybrid weighted communication network node importance evaluation method

Tian

Yang

et al. 2023

Front. Phys.

View full text Add to dashboard Cite

Communication networks are used as an important guarantee for information interaction and efficient collaboration within many fields and systems; however, under information technology conditions, the destruction of a number of nodes in a network may have a great impact on the overall operation of the network. Therefore, it is important to accurately determine the critical nodes in the network to enhance the network’s resistance to destruction. Combining the characteristic attributes of the communication network, a node contribution evaluation matrix is proposed based on the efficiency matrix, from the perspective of node receiving information; a node value evaluation matrix is proposed from the perspective of a node providing information to neighboring nodes, and node importance is calculated by integrating the evaluation results of the two matrices and the node’s own attributes. The algorithm is suitable for directed-weighted network node value evaluation, and the effectiveness and accuracy of the algorithm are verified by comparing other algorithms for a small-scale network. In further experimental validation, a hybrid weighted communication network evolution model based on organizational structured networks is proposed, and networks of different sizes are generated for experimental simulation. The results show that when nodes with high importance are removed from the network, they can cause a rapid decrease in the network efficiency and maximum connectivity, confirming the accuracy of the algorithm in evaluating the importance of nodes and identifying critical nodes in the network.

show abstract

Hierarchical attention neural network for information cascade prediction

Cited by 30 publications

References 39 publications

Intensity of SNS Use as a Predictor of Online Social Capital and the Moderating Role of SNS Platforms: An Empirical Study Using Partial Least Squares Structural Equation Modelling

Intensity of SNS Use as a Predictor of Online Social Capital and the Moderating Role of SNS Platforms: An Empirical Study Using Partial Least Squares Structural Equation Modelling

BERT4Loc: BERT for Location—POI Recommender System

Hybrid weighted communication network node importance evaluation method

Contact Info

Product

Resources

About