More Like this

1. Effective Seed-Guided Topic Discovery by Integrating Multiple Types of Contexts

   https://doi.org/10.1145/3539597.3570475  

   Zhang, Yu ; Zhang, Yunyi ; Michalski, Martin ; Jiang, Yucheng ; Meng, Yu ; Han, Jiawei ( February 2023 , ACM)

   Proceedings of the Sixteenth (Ed.)

   Instead of mining coherent topics from a given text corpus in a completely unsupervised manner, seed-guided topic discovery methods leverage user-provided seed words to extract distinctive and coherent topics so that the mined topics can better cater to the user’s interest. To model the semantic correlation between words and seeds for discovering topic-indicative terms, existing seedguided approaches utilize different types of context signals, such as document-level word co-occurrences, sliding window-based local contexts, and generic linguistic knowledge brought by pre-trained language models. In this work, we analyze and show empirically that each type of context information has its value and limitation in modeling word semantics under seed guidance, but combining three types of contexts (i.e., word embeddings learned from local contexts, pre-trained language model representations obtained from general-domain training, and topic-indicative sentences retrieved based on seed information) allows them to complement each other for discovering quality topics. We propose an iterative framework, SeedTopicMine, which jointly learns from the three types of contexts and gradually fuses their context signals via an ensemble ranking process. Under various sets of seeds and on multiple datasets, SeedTopicMine consistently yields more coherent and accurate topics than existing seed-guided topic discovery approaches. 

   more » « less
2. Using Topic Modeling for Code Discovery in Large Scale Text Data

   https://doi.org/https://doi.org/10.1007/978-3-030-67788-6_2  

   Cai, Zhiqiang ; Siebert-Evenstone, Amanda ; Eagan, Brendan R. ; Shaffer, David W. ( January 2021 , Advances in Quantitative Ethnography: Second International Conference, ICQE 2020, Malibu, CA, USA, February 1-3, 2021, Proceedings)

   Ruis, Andrew ; Lee, Seung B. (Ed.)

   When text datasets are very large, manually coding line by line becomes impractical. As a result, researchers sometimes try to use machine learning algorithms to automatically code text data. One of the most popular algorithms is topic modeling. For a given text dataset, a topic model provides probability distributions of words for a set of “topics” in the data, which researchers then use to interpret meaning of the topics. A topic model also gives each document in the dataset a score for each topic, which can be used as a non-binary coding for what proportion of a topic is in the document. Unfortunately, it is often difficult to interpret what the topics mean in a defensible way, or to validate document topic proportion scores as meaningful codes. In this study, we examine how keywords from codes developed by human experts were distributed in topics generated from topic modeling. The results show that (1) top keywords of a single topic often contain words from multiple human-generated codes; and conversely, (2) words from human-generated codes appear as high-probability keywords in multiple topic. These results explain why directly using topics from topic models as codes is problematic. However, they also imply that topic modeling makes it possible for researchers to discover codes from short word lists. 

   more » « less
3. Authorless Topic Models: Biasing Models Away from Known Structure

   Thompson, Laure ; Mimno, David ( January 2018 , COLING)

   Most previous work in unsupervised semantic modeling in the presence of metadata has assumed that our goal is to make latent dimensions more correlated with metadata, but in practice the exact opposite is often true. Some users want topic models that highlight differences between, for example, authors, but others seek more subtle connections across authors. We introduce three metrics for identifying topics that are highly correlated with metadata, and demonstrate that this problem affects between 30 and 50% of the topics in models trained on two real-world collections, regardless of the size of the model. We find that we can predict which words cause this phenomenon and that by selectively subsampling these words we dramatically reduce topic-metadata correlation, improve topic stability, and maintain or even improve model quality 

   more » « less
4. A deep semantic matching approach for identifying relevant messages for social media analysis

   https://doi.org/10.1038/s41598-023-38761-y  

   Biggers, Frederick Brown ; Mohanty, Somya D. ; Manda, Prashanti ( July 2023 , Scientific Reports)

   There is a growing interest in using social media content for Natural Language Processing applications. However, it is not easy to computationally identify the most relevant set of tweets related to any specific event. Challenging semantics coupled with different ways for using natural language in social media make it difficult for retrieving the most relevant set of data from any social media outlet. This paper seeks to demonstrate a way to present the changing semantics of Twitter within the context of a crisis event, specifically tweets during Hurricane Irma. These methods can be used to identify the most relevant corpus of text for analysis in relevance to a specific incident such as a hurricane. Using an implementation of the Word2Vec method of Neural Network training mechanisms to create Word Embeddings, this paper will: discuss how the relative meaning of words changes as events unfold; present a mechanism for scoring tweets based upon dynamic, relative context relatedness; and show that similarity between words is not necessarily static. We present different methods for training the vector model in Word2Vec for identification of the most relevant tweets for any search query. The impact of tuning parameters such as Word Window Size, Minimum Word Frequency, Hidden Layer Dimensionality, and Negative Sampling on model performance was explored. The window containing the local maximum for AU_ROC for each parameter serves as a guide for other studies using the methods presented here for social media data analysis.

    

   more » « less
5. Percolation-based topic modeling for tweets

   Churchill, R. ; Singh, L. ( August 2020 , WISDOM 2020 : The 9th KDD Workshop on Issues of Sentiment Discovery and Opinion Mining)

   This paper investigates topic modeling within a noisy domain. The goal is to generate topics that maximize topic coherence while introducing only a small amount of noise. The problem is motivated by the practical setting of short, noisy tweets, where it is important to generate topics containing a larger number of content words than noise words. For the most general version of this problem, we propose a new method, λ-CLIQ. It is a simple variant of the kclique percolation algorithm that employs for quasi-cliques during graph decomposition and percolation based on λ, a graph property variant. While the topics generated using our base algorithm are highly coherent, they are often contain too few words. To increase topic size, we add a post processing step that augments identified topic words using locally trained embeddings. We show that both λ-CLIQ and λ-CLIQ+ outperform the state of the art in terms of topic coherence on three distinct Twitter data sets. 

   more » « less