Generation of topic evolution graphs from short text streams

Gao, Wang; Peng, Min; Wang, Hua; Zhang, Yanchun; Han, Weiguang; Hu, Gang; Xie, Qianqian

doi:10.1016/j.neucom.2019.11.077

Cited by 32 publications

(9 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For modeling sequential time-series data with right granularity, Wang et al ( 2008 ) developed the continuous time dynamic topic model (cDTM). Topic content evolutionary graphs from short text streams are generated by an Online version of Conditional random field regularized correlated topic model (CCTM) to capture the evolution path of main topics and related subtopics (Gao et al, 2020 ). In fact, the evolutionary path can be explained by drifting among topics.…”

Section: Related Workmentioning

confidence: 99%

Evolution analysis of online topics based on ‘word-topic’ coupling network

Zhu

Qin

et al. 2022

Scientometrics

View full text Add to dashboard Cite

Analyzing topic evolution is an effective way to monitor the overview of topic spreading. Existing methods have focused either on the intensity evolution of topics along a timeline or the topic evolution path of technical literature. In this paper, we aim to study topic evolution from a micro perspective, which not only captures the topic timeline but also reveals the topic status and the directed evolutionary path among topics. Firstly, we construct a word network by co-occurrence relationship between feature words. Secondly, Latent Dirichlet allocation (LDA) model is used to automatically extract topics and capture the mapping relationship between words and topics, and then a ‘word-topic’ coupling network is built. Thirdly, based on the ‘word-topic’ coupling network, we describe the topic intensity evolution over time and measure topic status considering the contribution of feature words to a topic. The concept of topic drifting probability is proposed to identify the evolutionary path. Experimental results conducted on two real-world data sets of “COVID-19” demonstrate the effectiveness of our proposed method.

show abstract

Section: Related Workmentioning

confidence: 99%

Evolution analysis of online topics based on ‘word-topic’ coupling network

Zhu

Qin

et al. 2022

Scientometrics

View full text Add to dashboard Cite

show abstract

“…In recent years, knowledge representation learning has been a research hotspot due to its excellent performance in various tasks such as knowledge acquisition, integration, reasoning and topic evolution analysis [16,10,7,9]. Bordes et al proposed an unstructured model, which embed head and tail entities (h, t) into a vector space.…”

Section: Knowledge Representation Learningmentioning

confidence: 99%

Representation learning of knowledge graphs using convolutional neural networks

Gao¹,

Fang²,

Zhang³

et al. 2020

NNW

Self Cite

View full text Add to dashboard Cite

Knowledge graphs have been playing an important role in many Artificial Intelligence (AI) applications such as entity linking, question answering and so forth. However, most of previous studies focused on the symbolic representation of knowledge graphs with structural information, which cannot deal well with new entities or rare entities with little relevant knowledge. In this paper, we propose a new deep knowledge representation architecture that jointly encodes both structure and textual information. We first propose a novel neural model to encode the text descriptions of entities based on Convolutional Neural Networks (CNN). Secondly, an attention mechanism is applied to capture the valuable information from these descriptions. Then we introduce position vectors as supplementary information. Finally, a gate mechanism is designed to integrate representations of structure and text into the joint representation. Experimental results on two datasets show that our models obtain state-of-the-art results on link prediction and triplet classification tasks, and achieve the best performance on the relation classification task.

show abstract

“…This is due to the short length and high noise of tweets, and high levels of text overlap between the two categories. Probabilistic topic models may provide additional topic information for semantic differences, and the latest research on neural networks has shown that topic integration can improve the performance of NLP tasks such as summarization and question answering [ 8 , 11 , 38 ]. However, there is no standard method to integrate topic information with pre-trained language models such as BERT.…”

Section: Introductionmentioning

confidence: 99%

Identifying informative tweets during a pandemic via a topic-aware neural language model

Gao

Tao

et al. 2022

World Wide Web

Self Cite

View full text Add to dashboard Cite

Every epidemic affects the real lives of many people around the world and leads to terrible consequences. Recently, many tweets about the COVID-19 pandemic have been shared publicly on social media platforms. The analysis of these tweets is helpful for emergency response organizations to prioritize their tasks and make better decisions. However, most of these tweets are non-informative, which is a challenge for establishing an automated system to detect useful information in social media. Furthermore, existing methods ignore unlabeled data and topic background knowledge, which can provide additional semantic information. In this paper, we propose a novel Topic-Aware BERT (TABERT) model to solve the above challenges. TABERT first leverages a topic model to extract the latent topics of tweets. Secondly, a flexible framework is used to combine topic information with the output of BERT. Finally, we adopt adversarial training to achieve semi-supervised learning, and a large amount of unlabeled data can be used to improve inner representations of the model. Experimental results on the dataset of COVID-19 English tweets show that our model outperforms classic and state-of-the-art baselines.

show abstract

Generation of topic evolution graphs from short text streams

Cited by 32 publications

References 11 publications

Evolution analysis of online topics based on ‘word-topic’ coupling network

Evolution analysis of online topics based on ‘word-topic’ coupling network

Representation learning of knowledge graphs using convolutional neural networks

Identifying informative tweets during a pandemic via a topic-aware neural language model

Contact Info

Product

Resources

About