Improving LDA topic models for microblogs via tweet pooling and automatic labeling

By Rishabh Mehrotra, Scott Sanner, Wray L. Buntine, Lexing Xie. Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2013

511 citations recorded by the source corpus.

How researchers see this paper

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

Applications of Topic Models (2017, background): “To capture trends over time or across users, algorithms must also know connections between users or group messages together over time [Mehrotra et al., 2013].”
Semantics-driven Event Clustering in Twitter Feeds (2015, methodology): “We initialize this set as follows: Next to a set of topics for every tweet, we consider a dedicated hashtag pool H h for every hashtag h , by analogy with [12].”
Short Text Topic Modeling Techniques, Applications, and Performance: A Survey (2019, methodology): “Weng et al. [7] and Mehrotra et al. [17] aggregated tweets for pseudo-document using hashtags and the same user respectively.”
Improving Topic Models with Latent Feature Word Representations (2015, background): “One approach is to combine short texts into long pseudo-documents before training LDA (Hong and Davison, 2010; Weng et al., 2010; Mehrotra et al., 2013).”
#mytweet via Instagram: Exploring user behaviour across multiple social networks (2015, methodology): “We tackle this issue by author-time pooling of posts as described in [20]: Instead of a post being a single document, we treat a document as a collection of posts that have been shared within a predefined time interval by the user.”
Topic Modeling for Short Texts with Auxiliary Word Embeddings (2016, methodology): “Other metadata that have been used for short text aggregation include hashtags, timestamps, and named entities [13, 19, 42].”