Explicit time embedding based cascade attention network for information popularity prediction

Sun, Xigang; Zhou, Jingya; Liu, Ling; Wei, Wüchang

doi:10.1016/j.ipm.2023.103278

Cited by 15 publications

(10 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The cascade prediction method has developed rapidly in light of deep learning in recent years. Methods for cascaded graph processing have also received extensive attention [35,36]. Cheng et al [16] proposed the first deep learning-based information cascade prediction framework, DeepCas.…”

Section: Deep Learning-based Methodsmentioning

confidence: 99%

Dynamic End-to-End Information Cascade Prediction Based on Neural Networks and Snapshot Capture

Han

Meng

2023

Electronics

View full text Add to dashboard Cite

Knowing how to effectively predict the scale of future information cascades based on the historical trajectory of information dissemination has become an important topic. It is significant for public opinion guidance; advertising; and hotspot recommendation. Deep learning technology has become a research hotspot in popularity prediction, but for complex social platform data, existing methods are challenging to utilize cascade information effectively. This paper proposes a novel end-to-end deep learning network CAC-G with cascade attention convolution (CAC). This model can stress the global information when learning node information and reducing errors caused by information loss. Moreover, a novel Dynamic routing-AT aggregation method is investigated and applied to aggregate node information to generate a representation of cascade snapshots. Then, the gated recurrent unit (GRU) is employed to learn temporal information. This study’s validity and generalization ability are verified in the experiments by applying CAC-G on two public datasets where CAC-G is better than the existing baseline methods.

show abstract

Section: Deep Learning-based Methodsmentioning

confidence: 99%

Dynamic End-to-End Information Cascade Prediction Based on Neural Networks and Snapshot Capture

Han

Meng

2023

Electronics

View full text Add to dashboard Cite

show abstract

“…Various studies have been conducted that have adopted machine-learning approaches to automatically detect deontic clauses. Sun et al (2023) proposed a new method for BERT fine-tuning termed as DeonticBERT, classifying obligations, permissions, prohibitions, and other sentences from German tenancy law and Chinese social security policies, reported F1 scores of .89 (DeonticBERT) and .94 (BiLSTM). Liga and Palmirani (2022) found scores of .82 (obligations), .55 (permissions), .89 (constitutive rules) for the classification of obligations, permissions, and constitutive rules in 707 GDPR provisions by performing transfer learning based on BERT by leveraging the symbolic information of LegalXML formats.…”

Section: Related Workmentioning

confidence: 99%

“…DMC is a Natural Language Processing (NLP) task, in which, given a text with N normative statements S=(s 1 , s 2 , s 3 , ..., s n ), a classifier is trained to label deontic modalities in each statement (Sun et al, 2023). Limited datasets are available for DMC.…”

Section: Introductionmentioning

confidence: 99%

Low-Resource Deontic Modality Classification in EU Legislation

Minkova,

Chakravarthy,

Dijck

2023

Proceedings of the Natural Legal Language Processing Workshop 2023

View full text Add to dashboard Cite

In law, it is important to distinguish between obligations, permissions, prohibitions, rights, and powers. These categories are called deontic modalities. This paper evaluates the performance of two deontic modality classification models, LEGAL-BERT and a Fusion model, in a low-resource setting. To create a generalized dataset for multi-class classification, we extracted random provisions from European Union (EU) legislation. By finetuning previously researched and published models, we evaluate their performance on our dataset against fusion models designed for lowresource text classification. We incorporate focal loss as an alternative for cross-entropy to tackle issues of class imbalance. The experiments indicate that the fusion model performs better for both balanced and imbalanced data with a macro F1-score of 0.61 for imbalanced data, 0.62 for balanced data, and 0.55 with focal loss for imbalanced data. When focusing on accuracy, our experiments indicate that the fusion model performs better with scores of 0.91 for imbalanced data, 0.78 for balanced data, and 0.90 for imbalanced data with focal loss.

show abstract

“…The third characteristic of implicit learning is the comparative intricacy of occurrences. Empirical evidence in [1] suggests that individuals are capable of comprehending intricate information that would otherwise be challenging to grasp through explicit instruction. Consequently, the conditions conducive to implicit learning bear a striking resemblance to the situations commonly encountered by both young children and mature individuals in their everyday experiences.…”

Section: Introductionmentioning

confidence: 99%

The Importance of Implicit Knowledge in Chemistry Teaching and Learning

Dong

2023

JEBI

View full text Add to dashboard Cite

The term "implicit knowledge" encompasses a variety of subfields, including but not limited to experiential knowledge, tacit knowledge, and accidental learning paradigms. This article explores the concept of implicit knowledge and its perceived importance in the process of learning. The concept of tacit knowledge holds significant importance in the development of research aimed at investigating student cognition and comprehension in the field of chemistry, as well as in the analysis and application of research outcomes in educational settings. Literature on cognition argues that most knowledge, which individuals utilize when evaluating their environment and executing decisions is not available to conscious reflection. As a result, scholars in the realm of chemistry education must explore alternative methods to elicit tacit knowledge, which holds significant ramifications for their research endeavors. Hence, it is crucial to consider that the outcomes of numerous chemistry-related investigations, which document the conceptions of students, may reflect cognitive processes that rely on tacit knowledge to some extent. The differentiation between implicit and explicit information is paramount in understanding the cognitive process of learning chemistry, as the former operates subconsciously without conscious effort.

show abstract

Explicit time embedding based cascade attention network for information popularity prediction

Cited by 15 publications

References 60 publications

Dynamic End-to-End Information Cascade Prediction Based on Neural Networks and Snapshot Capture

Dynamic End-to-End Information Cascade Prediction Based on Neural Networks and Snapshot Capture

Low-Resource Deontic Modality Classification in EU Legislation

The Importance of Implicit Knowledge in Chemistry Teaching and Learning

Contact Info

Product

Resources

About