A Survey of Topic Models in Text Classification

As text data continues to grow quickly, it is increasingly important to develop intelligent systems to help people manage and make use of vast amounts of text data (big text data''). As a new family of effective general approaches to text data retrieval and analysis, probabilistic topic models---notably Probabilistic Latent Semantic Analysis (PLSA), Latent Dirichlet Allocations (LDA), and their many extensions---have been studied actively in the past decade with widespread applications. These topic models are powerful tools for extracting and analyzing latent topics contained in text data; they also provide a general and robust latent semantic representation of text data, thus improving many applications in information retrieval and text mining. Since they are general and robust, they can be applied to text data in any natural language and about any topics. This tutorial systematically reviews the major research progress in probabilistic topic models and discuss their applications in text retrieval and text mining. The tutorial provides (1) an in-depth explanation of the basic concepts, underlying principles, and the two basic topic models (i.e., PLSA and LDA) that have widespread applications, (2) an introduction to EM algorithms and Bayesian inference algorithms for topic models, (3) a hands-on exercise to allow the tutorial attendants to learn how to use the topic models implemented in the MeTA Open Source Toolkit and experiment with provided data sets, (4) a broad overview of all the major representative topic models that extend PLSA or LDA, and (5) a discussion of major challenges and future research directions.

The clinical notes in electronic health records have many possibilities for predictive tasks in text classification. The interpretability of these classification models for the clinical domain is critical for decision making. Using topic models for text classification of electronic health records for a predictive task allows for the use of topics as features, thus making the text classification more interpretable. However, selecting the most effective topic model is not trivial. In this work, we propose considerations for selecting a suitable topic model based on the predictive performance and interpretability measure for text classification. We compare 17 different topic models in terms of both interpretability and predictive performance in an inpatient violence prediction task using clinical notes. We find no correlation between interpretability and predictive performance. In addition, our results show that although no model outperforms the other models on both variables, our proposed fuzzy topic modeling algorithm (FLSA-W) performs best in most settings for interpretability, whereas two state-of-the-art methods (ProdLDA and LSI) achieve the best predictive performance.

Multi-label text classification is an increasingly important field as large amounts of text data are available and extracting relevant information is important in many application contexts. Probabilistic generative models are the basis of a number of popular text mining methods such as Naive Bayes or Latent Dirichlet Allocation. However, Bayesian models for multi-label text classification often are overly complicated to account for label dependencies and skewed label frequencies while at the same time preventing overfitting. To solve this problem we employ the same technique that contributed to the success of deep learning in recent years: greedy layer-wise training. Applying this technique in the supervised setting prevents overfitting and leads to better classification accuracy. The intuition behind this approach is to learn the labels first and subsequently add a more abstract layer to represent dependencies among the labels. This allows using a relatively simple hierarchical topic model which can easily be adapted to the online setting. We show that our method successfully models dependencies online for large-scale multi-label datasets with many labels and improves over the baseline method not modeling dependencies. The same strategy, layer-wise greedy training, also makes the batch variant competitive with existing more complex multi-label topic models.

Topic modeling extracts useful potential topics that reflect market information from massive financial news and is widely used in data mining and economic research. Traditional topic modeling approaches such as Latent Dirichlet Allocation (LDA) and Non-Negative Matrix Factorization (NMF) lack semantic information, and short texts have feature sparse problems. We develop a topic clustering model based on BERT-LDA joint embedding that takes both contextual semantics and thematic narrative into account. We cluster document embeddings with the HDBSCAN algorithm and utilize a class-based TF-IDF (c-TF-IDF) method to create topic representations. Empirical results show that the BERT-LDA model is competitive compared with traditional and single topic models. It generates coherent topic words that are dissimilar to each other.

Integrating Big Data Into Evaluation: R Code for Topic Identification and Modeling

Natural language processing technologies, such as topic models, have been proven to be effective for scholarly recommendation tasks with the ability to deal with content information. Recently, venue recommendation is becoming an increasingly important research task due to the unprecedented number of publication venues. However, traditional methods focus on either the author’s local network or author-venue similarity, where the multiple relationships between scholars and venues are overlooked, especially the venue–venue interaction. To solve this problem, we propose an author topic model–enhanced joint graph modeling approach that consists of venue topic modeling, venue-specific topic influence modeling, and scholar preference modeling. We first model the venue topic with Latent Dirichlet Allocation. Then, we model the venue-specific topic influence in an asymmetric and low-dimensional way by considering the topic similarity between venues, the top-influence of venues, and the top-susceptibility of venues. The top-influence characterizes venues’ capacity of exerting topic influence on other venues. The top-susceptibility captures venues’ propensity of being topically influenced by other venues. Extensive experiments on two real-world datasets show that our proposed joint graph modeling approach outperforms the state-of-the-art methods.

Objective: To exemplify how topic modeling can be used in management research, my objectives are two-fold. First, I introduce topic modeling as a social sciences research tool and map critical published studies in management and other social sciences that employed topic modeling in a proper manner. Second, I illustrate how to do topic modeling by applying topic modeling in an analysis of the last five years of published research in this journal: the Iberoamerican Journal of Strategic Management (IJSM). Methodology: I analyze the last five years (2014 to 2018) of published articles in the IJSM. The sample is 164 articles. The abstracts were subjected to a standard topic modeling text pre-processing routine, generating 1,252 unique tokens. Originality/Relevance: By proposing topic modeling as a valid and opportunistic methodology for analyzing textual data, it can shift the old paradigm that textual data belongs only to the qualitative realm. Furthermore, allowing textual data to be labeled and quantified in a reproducible manner that mitigates (or closely fully eliminates) researcher bias. Main Results: Six topics were generated through Latent Dirichlet Allocation (LDA): Topic 1 – Strategy and Competitive Advantage; Topic 2 – International Business and Top Management Team; Topic 3 – Entrepreneurship; Topic 4 – Learning and Cooperation; Topic 5 – Finance and Strategy; and Topic 6 – Dynamic Capabilities. Theoretical/methodological Contributions: I present the state of the art of the literature published in IJSM and also show how the reader can perform their own topic modeling. The full data and code that was used are available in free open science repositories in Open Science Framework (OSF) and GitHub.

Topic modelling is an important technique for extracting meaningful insights from large volumes of unstructured text data. The paper presents a federated technique for topic modelling that is based on a novel approach of the Latent Dirichlet Allocation (LDA) method for topic model generation. The proposed approach enables a topic model to be developed in a distributed environment using data continually generated from multiple sources without the need for sharing actual data. The first iteration of the topic modelling uses unsupervised LDA at each device generating the data. The results of each device are aggregated at a central server to generate a set of seed words that are used for guided LDA by the subsequent iterations of topic modelling. The proposed work, Federated LDA (F-LDA) has been evaluated using two datasets: a text dataset of dialogues between patients and doctors based on factual conversations and another comprising tweets related to depression. Comparing the performance of F-LDA with that of a centralized LDA, it was observed that F-LDA results in improved coherence score as well as diversity score in comparison to centralized LDA. This indicates that F-LDA achieves better interpretable topics covering a wide range of themes without redundancy.

A short text topic modeling method based on integrating Gaussian and Logistic coding networks with pre-trained word embeddings

How to Improve Text Summarization and Classification by Mutual Cooperation on an Integrated Framework

We present a new way called Persona Analysis with Text Topic Modelling (PATTM), which tries to learn the role of personae according to the literal descriptions. It is similar to Latent Dirichlet Allocation (LDA) and Author Topic (AT) model, with the attribute of allowing all text to join in the topic modelling process, even when there is no persona in the text. We experiment on the “Libya Event” data set which contains more than 4,000 texts collected from the Internet. The PATTM gives lower perplexity than LDA and AT model on the data set.

Topic modeling is the statistical model for discovering hidden topics or keywords in a collection of documents. Topic modeling is also considered a probabilistic model for learning, analyzing, and discovering topics from the document collection. The most popular techniques for topic modeling are latent semantic analysis (LSA), probabilistic latent semantic analysis (pLSA), latent Dirichlet allocation (LDA), and the recent deep learning-based lda2vec. LDA is most commonly used in extractive multi-document summarization to determine whether the extracted sentence reflects the concept of the input document. In this paper, we will try to explore various multi-document summarization techniques that use LDA as a topic modeling method for improving final summary coverage and to reduce redundancy. Finally, we compared LDA and LSA using the Genism toolkit, and our experiment results show that LDA outperforms LSA if we increase the number of features considered for sentence selection.KeywordsTopic modelingText summarizationLDALSA

This study aims to assess the effectiveness of topic modeling in the English translation of the Holy Quran. Topic modeling is a popular text mining technique for uncovering latent semantic patterns in the collection of textual documents and helps to annotate the documents based on these topics. This study identifies the most significant topics in each document as well as grasping an understanding of the topic distribution throughout the document sets. Different steps are performed to acquire the dominant topics in each document and identify the distribution of topics across documents. In this context, the present research work chose to employ Latent Dirichlet Allocation as an unsupervised approach for topic modeling since there is no requirement for a training phase as hidden topics can be discovered throughout the topic modeling process. For this, the word cloud is generated to understand and interpret the results after pre-processing. A dictionary and corpus are created to extract the features from the dataset using the Bag of Words approach. The results are evaluated by calculating the perplexity and coherence score, where high coherence indicates the goodness of well-structured topic models and low perplexity score indicates the correctness of prediction made by the topic models. Lastly, the visualization step is performed.

This paper focuses on two types of modeling of information flow in news stream, namely, burst analysis and topic modeling. First, when one wants to detect a kind of topics that are paid much more attention than usual, it is usually necessary for him/her to carefully watch every article in news stream at every moment. In such a situation, it is well known in the field of time series analysis that Kleinberg’s modeling of bursts is quite effective in detecting burst of keywords. Second, topic models such as LDA (latent Dirichlet allocation) are also quite effective in estimating distribution of topics over a document collection such as articles in news stream. However, Kleinberg’s modeling of bursts is usually applied only to bursts of keywords but not to those of topics. Considering this fact, we propose how to apply Kleinberg’s modeling of bursts to topics estimated by a topic model such as LDA and DTM (dynamic topic model).

Along with the exponential growth of text data on the Web, particularly of the user-generated content, comes an increasing need for hierarchically organizing documents, retrieving documents accurately, and discovering evolutionary trends of various popular topics from the data. However, all of these are challenging due to the diversity, heterogeneity, noisiness and time-sensitivity of Web 2.0 data. Motivated by this, we tackle the challenges at a fundamental level, by proposing a novel topic modeling method with ontological guidance. It may be used to discover topic language models formalizing various terms relevant to given topics using the Web data. The topic model takes into account both the ontological relationships amongst the topics defined in a topic taxonomy and also word co-occurrence patterns in the data to automatically identify the portions in the data relevant to the topics. Then, it estimates language models for these topics from these relevant portions. At an application level, we use the topic model to propose novel approaches for three different tasks, namely hierarchical text classification without labeled data, information retrieval with pseudo-relevance feedback, and discovering topic evolutionary trends. Our classification experiment on the IPTC (International Press and Telecommunications Council) taxonomy, containing more than 1100 topics, shows that our approach achieves a performance of 67% in terms of the hierarchical version of the F-1 measure, without using any labeled data. Our retrieval experiments on five benchmark datasets show that compared to baseline retrieval (without pseudo-relevance feed-back), our approach improves on average 39% in terms of mean average precision. Finally, for the last task, using blog data, our approach discovers meaningful insights on how the crowd responds to various news topics such as the language used to discuss each topic, how this language drifts over time, and when the crowd’s focus on a topic increases, reaches a peak, and declines.