Understanding Twitter Hashtags from Latent Themes Using Biterm Topic Model

2019 ◽  
Vol 13 ◽  
Author(s):  
Muzafar Rasool Bhat ◽  
Burhan Bashir ◽  
Majid A. Kundroo ◽  
Naffi A. Ahanger
Keyword(s):  
Social Media ◽  
Latent Dirichlet Allocation ◽  
Topic Model ◽  
Social Issues ◽  
Text Messages ◽  
Short Message ◽  
Short Text ◽  
Contemporary Issue ◽  
Significant Length ◽  
Latent Topic

Social media in general and Twitter in particular provides a space for discourses, contemporary narratives besides a discussion about few specific social issues. People respond to these events by writing short text messages. Background: Hashtag “#”, a specific way to respond to a given raised discourse, narrative or any contemporary issue is usual to social media. Netizens write a short message as their opinion about any given issue represented using a given Hashtag. These small messages generally tend to have a latent topic (theme) as one’s opinion about it. Objective: This research is aimed to extract, represent and understand those hidden themes Method: Biterm Topic Model (BTM) has been used in this study given its ability to deal with the short messages unlike Latent Dirichlet Allocation that expects a document to have a significant length. Results: Twitter Hashtag #MeToo has been used in this research with forty thousand (40,000) comments. Data has been modelled with ten (10) topics after verifying suitable number of topics from four metrics Griffths, CaoJuan, Arun and Deveaud. Conclusion: The experimental results show that the proposed approach to understand the twittter hashtages from latent themes using biterm topic modelling method is very effective as compared to other methods

Topic-BERT: Detecting harmful information from social media

2021 ◽  
pp. 1-10
Author(s):  
Wang Gao ◽  
Hongtao Deng ◽  
Xun Zhu ◽  
Yuan Fang
Keyword(s):  
Social Media ◽  
Language Processing ◽  
Topic Model ◽  
Classification Performance ◽  
Critical Research ◽  
Short Text ◽  
Additional Information ◽  
Proposed Model ◽  
Weight Calculation ◽  
Two Stages

Harmful information identification is a critical research topic in natural language processing. Existing approaches have been focused either on rule-based methods or harmful text identification of normal documents. In this paper, we propose a BERT-based model to identify harmful information from social media, called Topic-BERT. Firstly, Topic-BERT utilizes BERT to take additional information as input to alleviate the sparseness of short texts. The GPU-DMM topic model is used to capture hidden topics of short texts for attention weight calculation. Secondly, the proposed model divides harmful short text identification into two stages, and different granularity labels are identified by two similar sub-models. Finally, we conduct extensive experiments on a real-world social media dataset to evaluate our model. Experimental results demonstrate that our model can significantly improve the classification performance compared with baseline methods.

scholarly journals A word embedding topic model for topic detection and summary in social networks

2019 ◽  
Vol 52 (9-10) ◽  
pp. 1289-1298 ◽  
Author(s):  
Lei Shi ◽  
Gang Cheng ◽  
Shang-ru Xie ◽  
Gang Xie
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Latent Dirichlet Allocation ◽  
Semantic Analysis ◽  
Topic Model ◽  
Word Embedding ◽  
Probabilistic Latent Semantic Analysis ◽  
Topic Detection ◽  
Short Text ◽  
Internal Relationship

The aim of topic detection is to automatically identify the events and hot topics in social networks and continuously track known topics. Applying the traditional methods such as Latent Dirichlet Allocation and Probabilistic Latent Semantic Analysis is difficult given the high dimensionality of massive event texts and the short-text sparsity problems of social networks. The problem also exists of unclear topics caused by the sparse distribution of topics. To solve the above challenge, we propose a novel word embedding topic model by combining the topic model and the continuous bag-of-words mode (Cbow) method in word embedding method, named Cbow Topic Model (CTM), for topic detection and summary in social networks. We conduct similar word clustering of the target social network text dataset by introducing the classic Cbow word vectorization method, which can effectively learn the internal relationship between words and reduce the dimensionality of the input texts. We employ the topic model-to-model short text for effectively weakening the sparsity problem of social network texts. To detect and summarize the topic, we propose a topic detection method by leveraging similarity computing for social networks. We collected a Sina microblog dataset to conduct various experiments. The experimental results demonstrate that the CTM method is superior to the existing topic model method.

Identifying target audience on enterprise social network

2019 ◽  
Vol 119 (1) ◽  
pp. 111-128 ◽  
Author(s):  
Jianhong Luo ◽  
Xuwei Pan ◽  
Shixiong Wang ◽  
Yujing Huang
Keyword(s):  
Social Media ◽  
Social Network ◽  
Latent Dirichlet Allocation ◽  
Topic Model ◽  
Information Service ◽  
Target Audience ◽  
Business Practices ◽  
Content Type ◽  
Enterprise Social Media ◽  
Enterprise Social Network

Purpose Delivering messages and information to potentially interested users is one of the distinguishing applications of online enterprise social network (ESN). The purpose of this paper is to provide insights to better understand the repost preferences of users and provide personalized information service in enterprise social media marketing. Design/methodology/approach It is accomplished by constructing a target audience identification framework. Repost preference latent Dirichlet allocation (RPLDA) topic model topic model is proposed to understand the mass user online repost preferences toward different contents. A topic-oriented preference metric is proposed to measure the preference degree of individual users. And the function of reposting forecasting is formulated to identify target audience. Findings The empirical research shows the following: a total of 20 percent of the repost users in ESN represent the key active users who are particularly interested in the latent topic of messages in ESN and fits Pareto distribution; and the target audience identification framework can successfully identify different target key users for messages with different latent topics. Practical implications The findings should motivate marketing managers to improve enterprise brand by identifying key target audience in ESN and marketing in a way that truthfully reflects personalized preferences. Originality/value This study runs counter to most current business practices, which tend to use simple popularity to seek important users. Adaptively and dynamically identifying target audience appears to have considerable potential, especially in the rapidly growing area of enterprise social media information service.

scholarly journals Latent Topic Estimation Based on Events in a Document

2012 ◽  
Vol 16 (5) ◽  
pp. 603-610
Author(s):  
Risa Kitajima ◽  
◽  
Ichiro Kobayashi
Keyword(s):  
Text Analysis ◽  
Latent Dirichlet Allocation ◽  
Topic Model ◽  
Latent Semantic Indexing ◽  
Document Retrieval ◽  
Retrieval Task ◽  
Latent Topic ◽  
Latent Topics ◽  
Definition Of ◽  
The Relationship

Several latent topic model-based methods such as Latent Semantic Indexing (LSI), Probabilistic LSI (pLSI), and Latent Dirichlet Allocation (LDA) have been widely used for text analysis. These methods basically assign topics to words, however, and the relationship between words in a document is therefore not considered. Considering this, we propose a latent topic extraction method that assigns topics to events that represent the relation between words in a document. There are several ways to express events, and the accuracy of estimating latent topics differs depending on the definition of an event. We therefore propose five event types and examine which event type works well in estimating latent topics in a document with a common document retrieval task. As an application of our proposed method, we also show multidocument summarization based on latent topics. Through these experiments, we have confirmed that our proposed method results in higher accuracy than the conventional method.

scholarly journals Analyzing Sentiments and Diffusion Characteristics of COVID-19 Vaccine Misinformation Topics in Social Media

2022 ◽  
Vol 9 (3) ◽  
pp. 1-22
Author(s):  
Mohammad Daradkeh
Keyword(s):  
Social Media ◽  
Data Analytics ◽  
Latent Dirichlet Allocation ◽  
Topic Model ◽  
Diffusion Characteristics ◽  
Sentiment Orientation ◽  
Positive Sentiment ◽  
Negative Sentiment ◽  
And Diffusion ◽  
Machine Learning Models

This study presents a data analytics framework that aims to analyze topics and sentiments associated with COVID-19 vaccine misinformation in social media. A total of 40,359 tweets related to COVID-19 vaccination were collected between January 2021 and March 2021. Misinformation was detected using multiple predictive machine learning models. Latent Dirichlet Allocation (LDA) topic model was used to identify dominant topics in COVID-19 vaccine misinformation. Sentiment orientation of misinformation was analyzed using a lexicon-based approach. An independent-samples t-test was performed to compare the number of replies, retweets, and likes of misinformation with different sentiment orientations. Based on the data sample, the results show that COVID-19 vaccine misinformation included 21 major topics. Across all misinformation topics, the average number of replies, retweets, and likes of tweets with negative sentiment was 2.26, 2.68, and 3.29 times higher, respectively, than those with positive sentiment.

scholarly journals Filtering and Classifying Relevant Short Text with a Few Seed Words

2019 ◽  
Vol 3 (3) ◽  
pp. 165-186 ◽  
Author(s):  
Chenliang Li ◽  
Shiqian Chen ◽  
Yan Qi
Keyword(s):  
Latent Dirichlet Allocation ◽  
Topic Model ◽  
State Of The Art ◽  
Superior Performance ◽  
Support Vector ◽  
Short Text ◽  
Text Filtering ◽  
Supervised Classifiers ◽  
Real World Datasets ◽  
Weakly Supervised

Abstract Filtering out irrelevant documents and classifying the relevant ones into topical categories is a de facto task in many applications. However, supervised learning solutions require extravagant human efforts on document labeling. In this paper, we propose a novel seed-guided topic model for dataless short text classification and filtering, named SSCF. Without using any labeled documents, SSCF takes a few “seed words” for each category of interest, and conducts short text filtering and classification in a weakly supervised manner. To overcome the issues of data sparsity and imbalance, the short text collection is mapped to a collection of pseudodocuments, one for each word. SSCF infers two kinds of topics on pseudo-documents: category-topics and general-topics. Each category-topic is associated with one category of interest, covering the meaning of the latter. In SSCF, we devise a novel word relevance estimation process based on the seed words, for hidden topic inference. The dominating topic of a short text is identified through post inference and then used for filtering and classification. On two real-world datasets in two languages, experimental results show that our proposed SSCF consistently achieves better classification accuracy than state-of-the-art baselines. We also observe that SSCF can even achieve superior performance than the supervised classifiers supervised latent dirichlet allocation (sLDA) and support vector machine (SVM) on some testing tasks.

scholarly journals A New Vector Representation of Short Texts for Classification

2019 ◽  
Vol 17 (2) ◽  
pp. 241-249
Author(s):  
Yangyang Li ◽  
Bo Liu
Keyword(s):  
Text Classification ◽  
Web Search ◽  
Latent Dirichlet Allocation ◽  
Topic Model ◽  
Classification Performance ◽  
New Method ◽  
Data Sets ◽  
Text Data ◽  
Short Text ◽  
Space Model

Short and sparse characteristics and synonyms and homonyms are main obstacles for short-text classification. In recent years, research on short-text classification has focused on expanding short texts but has barely guaranteed the validity of expanded words. This study proposes a new method to weaken these effects without external knowledge. The proposed method analyses short texts by using the topic model based on Latent Dirichlet Allocation (LDA), represents each short text by using a vector space model and presents a new method to adjust the vector of short texts. In the experiments, two open short-text data sets composed of google news and web search snippets are utilised to evaluate the classification performance and prove the effectiveness of our method.

Use of a Latent Topic Model for Characteristic Extraction from Health Checkup Questionnaire Data

2015 ◽  
Vol 54 (06) ◽  
pp. 515-521 ◽  
Author(s):  
I. Miyano ◽  
H. Kataoka ◽  
N. Nakajima ◽  
T. Watabe ◽  
N. Yasuda ◽  
...  
Keyword(s):  
Hierarchical Clustering ◽  
Latent Dirichlet Allocation ◽  
Topic Model ◽  
Probability Model ◽  
Model Parameters ◽  
Questionnaire Data ◽  
Health Checkup ◽  
Subjective Data ◽  
Latent Topic ◽  
Study Participants

Summary Objectives: When patients complete questionnaires during health checkups, many of their responses are subjective, making topic extraction difficult. Therefore, the purpose of this study was to develop a model capable of extracting appropriate topics from subjective data in questionnaires conducted during health checkups. Methods: We employed a latent topic model to group the lifestyle habits of the study participants and represented their responses to items on health checkup questionnaires as a probability model. For the probability model, we used latent Dirichlet allocation to extract 30 topics from the questionnaires. According to the model parameters, a total of 4381 study participants were then divided into groups based on these topics. Results from laboratory tests, including blood glucose level, triglycerides, and estimated glomerular filtration rate, were compared between each group, and these results were then compared with those obtained by hierarchical clustering. Results: If a significant (p < 0.05) difference was observed in any of the laboratory measurements between groups, it was considered to indicate a questionnaire response pattern corresponding to the value of the test result. A comparison between the latent topic model and hierarchical clustering grouping revealed that, in the latent topic model method, a small group of participants who reported having subjective signs of uri-nary disorder were allocated to a single group. Conclusions: The latent topic model is useful for extracting characteristics from a small number of groups from questionnaires with a large number of items. These results show that, in addition to chief complaints and history of past illness, questionnaire data obtained during medical checkups can serve as useful judgment criteria for assessing the conditions of patients.

SenU-PTM: a novel phrase-based topic model for short-text topic discovery by exploiting word embeddings

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Heng-Yang Lu ◽  
Yi Zhang ◽  
Yuntao Du
Keyword(s):  
Latent Dirichlet Allocation ◽  
Topic Model ◽  
Second Phase ◽  
Word Embeddings ◽  
Two Phase ◽  
Content Type ◽  
Short Text ◽  
Topic Discovery ◽  
Two Phases ◽  
Sense Unit

PurposeTopic model has been widely applied to discover important information from a vast amount of unstructured data. Traditional long-text topic models such as Latent Dirichlet Allocation may suffer from the sparsity problem when dealing with short texts, which mostly come from the Web. These models also exist the readability problem when displaying the discovered topics. The purpose of this paper is to propose a novel model called the Sense Unit based Phrase Topic Model (SenU-PTM) for both the sparsity and readability problems.Design/methodology/approachSenU-PTM is a novel phrase-based short-text topic model under a two-phase framework. The first phase introduces a phrase-generation algorithm by exploiting word embeddings, which aims to generate phrases with the original corpus. The second phase introduces a new concept of sense unit, which consists of a set of semantically similar tokens for modeling topics with token vectors generated in the first phase. Finally, SenU-PTM infers topics based on the above two phases.FindingsExperimental results on two real-world and publicly available datasets show the effectiveness of SenU-PTM from the perspectives of topical quality and document characterization. It reveals that modeling topics on sense units can solve the sparsity of short texts and improve the readability of topics at the same time.Originality/valueThe originality of SenU-PTM lies in the new procedure of modeling topics on the proposed sense units with word embeddings for short-text topic discovery.

Incorporating Biterm Correlation Knowledge into Topic Modeling for Short Texts

2020 ◽  
Author(s):  
Kai Zhang ◽  
Yuan Zhou ◽  
Zheng Chen ◽  
Yufei Liu ◽  
Zhuo Tang ◽  
...  
Keyword(s):  
Topic Modeling ◽  
Latent Dirichlet Allocation ◽  
Topic Model ◽  
Semantic Knowledge ◽  
Superior Performance ◽  
Knowledge Based ◽  
Modeling Process ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
Latent Topic

Abstract The prevalence of short texts on the Web has made mining the latent topic structures of short texts a critical and fundamental task for many applications. However, due to the lack of word co-occurrence information induced by the content sparsity of short texts, it is challenging for traditional topic models like latent Dirichlet allocation (LDA) to extract coherent topic structures on short texts. Incorporating external semantic knowledge into the topic modeling process is an effective strategy to improve the coherence of inferred topics. In this paper, we develop a novel topic model—called biterm correlation knowledge-based topic model (BCK-TM)—to infer latent topics from short texts. Specifically, the proposed model mines biterm correlation knowledge automatically based on recent progress in word embedding, which can represent semantic information of words in a continuous vector space. To incorporate external knowledge, a knowledge incorporation mechanism is designed over the latent topic layer to regularize the topic assignment of each biterm during the topic sampling process. Experimental results on three public benchmark datasets illustrate the superior performance of the proposed approach over several state-of-the-art baseline models.

Sign in / Sign up

Export Citation Format

Share Document