Comparing Twitter and Traditional Media Using Topic Models

By Wayne Xin Zhao, Jing Jiang, Jianshu Weng, Jing He, Ee-Peng Lim, Hongfei Yan, Xiaoming Li. European Conference on Information Retrieval, 2011

1,335 citations recorded by the source corpus.

Subfields: Communication, Information Systems, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/49ae87c25dbad1ed88256b175459ce1c81f445ac

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Communication

In Information Systems

In Statistical and Nonlinear Physics

Citations in the corpus

Understanding the Limiting Factors of Topic Modeling via Posterior Contraction Analysis (2014, methodology): “Alternatively, arbitrary manipulations of the LDA model have to be introduced in order to adapt the topic model to a particular context (e.g., Mimno & McCallum (2007); Zhao et al. (2011); Carman et al. (2010)).”
Topic Aware Neural Response Generation (2016, methodology): “We obtain topic words of a message from a Twitter LDA model (Zhao et al. 2011).”
A Survey on Dialogue Systems: Recent Advances and New Frontiers (2017, methodology): “y tree matching patterns and used them as sparse one-hot inputs of a deep feed-forward neural network for context-response matching. [105] incorporated the topic vector generated by Twitter LDA model [121] into the CNN based structure to boost responses with rich content. 3.2.2 Multiturn Response Ma”
Improving Topic Models with Latent Feature Word Representations (2015, background): “Another approach is to assume that there is only one topic per document (Nigam et al., 2000; Zhao et al., 2011; Yin and Wang, 2014).”
A biterm topic model for short texts (2013, methodology): “Some others tried to aggregate short texts into lengthy pseudo-documents based on some additional information, and then train conventional topic models [32, 35].”
Improving LDA topic models for microblogs via tweet pooling and automatic labeling (2013, methodology): “[15] compared topic characteristics between Twitter and a traditional news medium – the New York Times; they propose to use one topic per tweet (similar to PLSA), and argue that this is better than the Unpooled LDA scheme and the author-topic model.”
Short Text Topic Modeling Techniques, Applications, and Performance: A Survey (2019, methodology): “Other information includes hashtags, timestamps, and named entities have been tread as metadata to merging short texts [17], [19], [38].”
Spatiotemporal social media analytics for abnormal event detection and examination using seasonal-trend decomposition (2012, background): “Similarly, there are many related works for non-spatial temporal document collections, for example IN-SPIRE [36], which is a general purpose document analysis system that depicts document clusters on a visual landscape of topics.”
Truth Inference in Crowdsourcing: Is the Problem Solved? (2017, methodology): “For example, existing studies [19, 35] make use of the text description in each task and adopt topic model techniques [6, 56] to generate a vector of sizeK for the task; while Multi [51] learns aK-size vector without referring to external information (e.”
Survey on evaluation methods for dialogue systems (2019, methodology): “(2017) add a topic-attention mechanism in their generation architecture, which takes as inputs topic words which are extracted using the Twitter LDA model (Zhao et al. 2011).”
DeepHate: Hate Speech Detection via Multi-Faceted Text Representations (2020, background): “Often, in mining topics from Twitter posts, the documents are formed by aggregating the posts by hashtags, published time, or authors [23, 48].”
Like It or Not (2016, methodology): “This dataset has been also used to address other tasks applied on Twitter such as microblog search [Naveed et al. 2011] and topic modeling [Zhao et al. 2011].”
Latent Dirichlet allocation (LDA) and topic modeling: models, applications, a survey (2017, methodology): “Some of works related based on LDA and Gibbs, such as [61, 97, 108, 114, 124, 127, 150, 154, 175, 183, 198].”
Topic Augmented Neural Response Generation with a Joint Attention Mechanism (2016, methodology): “In training, we concatenate the post and the response of each sample to form a short document and employ the collapsed Gibbs sampling algorithm (Zhao et al., 2011) to estimate the parameters.”
Searching microblogs: coping with sparsity and document quality (2011, background): “[17] that observed that a single tweet usually covers a single topic.”