Questions tagged [topic-models]

A topic model is a type of statistical model for discovering the abstract "topics" that occur in a collection of documents.

Filter by
Sorted by
Tagged with
0
votes
0answers
11 views

Using Topic Modeling for Text Classification

I'm trying to use topic modeling using Latent Dirichlet Allocation as input for text classification problem. Although, I'm not getting good results by doing this. The data has three variables doc id, ...
0
votes
0answers
2 views

Perplexity Score for Topic modelling

I am new to topic modelling using LDA. I build a initial version of topic modelling. I tried different topic models. I got to know that perplexity score is a good measure for evaluating topic models. ...
1
vote
0answers
14 views

Meaning of $P(d)$ in pLSA

Given the following equation: $$ {\displaystyle P(w,d)=P(d)\sum _{c}P(c|d)P(w|c)} $$ How $P(d)$ is calculated? I suggest that's relative length of the document with respect to corpus: $$ P(d)=\frac{\...
1
vote
0answers
16 views

Interpretation of negative values in the results of LSA

How can I interpret the results of LSA? From the following table, I can understand that documents 0 and 1 (dealing with cats) fall into Topic 2. Document 4, which talks about both dog and cat, falls ...
0
votes
0answers
13 views

I'm trying to identify the posterior distributions in LDiA. Are theta and phi in this PGM the posterior distributions of LDiA?

My understanding is that alpha and beta are the dirichlet priors, and the posteriors would be theta and phi. And since theta and phi are from the same family of distributions as alpha and beta, the ...
1
vote
1answer
19 views

In Latent Dirichlet allocation, is the following formula the probability of observing a single document, or an entire corpus?

This is the formula in question: Source: https://en.wikipedia.org/wiki/Latent_Dirichlet_allocation
0
votes
0answers
8 views

Difference between Structural Topic Modeling(STM) and SAGE (Sparse Additive Generative Model)?

I have read that STM combines 3 models of: (1) correlated topic model (CTM) (2) Dirichlet-Multinomial Regression (DMR) topic model (3) Sparse Additive Generative Model (SAGE) Is it correct to just ...
0
votes
0answers
6 views

Does the number of topics change based on the type of model?

I am working on a classification of some tweets regarding biomasses. I have made a classification with LDA using 75 topics (found by using the ldatuning library). Everything went alright, topics were ...
1
vote
1answer
26 views

Topic modeling for regression

Is there a way to influence the way topics are created with topic modelling in the sense that the topics also reflect their influence on the target variable of a machine learning problem? I have a ...
0
votes
0answers
5 views

Number of topics - Topic Model(BTM)

I would like to know if it could be a good idea, in order to find the optimal number of topics in a topic model (in my particular case a BTM), to look at the mean of the topics coherence scores and ...
0
votes
0answers
13 views

BTM - Classification per topic

I have been given a task in which I have to classify some tweets per topic. I have created , in R, a model using BTM, which means I have the probability of each word belonging to each topic. Shouldn't ...
0
votes
0answers
11 views

No “elbow” with LDA measures c_v & uMass

I am doing some topic modelling experiments - for learning purposes only - with LDA against just over 50k hotel reviews. I am using the c_v and uMass coherence scores but I see no significant change ...
1
vote
1answer
36 views

Latent Dirichlet Allocation - dimensionality of the Dirichlet prior parameter

I seeking some clarity on the dimensionality of the (hyper)parameter $\eta$ of the "smoothed LDA" model in Section 5.4 of the original paper by Blei, Ng, Jordan (2003), which can be found ...
0
votes
0answers
21 views

online LDA with R (topic modelling)

Topic modelling based on online LDA continously updates the model with new data without having to refit the model using the full dataset, ideally without an a priori known vocabulary. This makes it ...
0
votes
0answers
52 views

Using KL divergence to select topic from LDA

I have used sklearn's sklearn.decomposition.LatentDirichletAllocation module to model 10 topics in a set of documents. I have also used the same on a reference text (1 document) and obtained a 1 topic ...
0
votes
0answers
22 views

Gibbs Sampling in LDA - any other inference procedures?

I am playing with the LDA model in python and would like to ask if anyone knows whether Python's toolkits for LDA (gensim/scikit-learn), have all implemented the Gibbs Sampling inside or is there any ...
0
votes
0answers
36 views

Topic Modeling: topic coherence score by each topic

I'm currently using NMF, but I am just curious whether I can have coherence scores for each topic. For instance, i want to see whether topic 5 is trained better than topic 1. By looking at the ...
0
votes
0answers
19 views

Interpretation of token weights in LDA topic model?

I'm using Gensim's LDA model for some topic modeling. Once the model has trained, it provides for each topic a coherence score, as well as a list of tuples of weights and tokens. The latter could for ...
0
votes
1answer
25 views

Suggestions for identifying the most “important” image labels

I have a table with images and their assigned object (i.e. specific sub-parts) and image (i.e. image as a whole) labels. Each image may have multiple object labels but only 2 whole-image labels. I ...
1
vote
0answers
17 views

How to know if LDA(Latent Dirichlet Allocation) is applicable to a particular problem? [closed]

Suppose my database has many tables and each table has many columns. I want to use column names of all tables to figure out "major data contents" in my database. Example columns are ...
0
votes
0answers
16 views

Browser history topic clustering

I have a detailed browser history where each event has a visit time, visit duration, URL, and page title. For example let's consider this browser history (page titles only): is Thailand open for ...
0
votes
0answers
25 views

Extract Keyword/Concept From Column Description Using NLP

Suppose in my database, each table has a description associated with each column and I want to further extract keyword or key concept from the description. For example, mean of transaction amount in ...
0
votes
0answers
9 views

Balanced corpus in topic models

I am building a topic model for a corpus of webpages extracted from a random subset of domains, the topics seems to be ok, but often I see very similar topics, which makes me think I should reduce the ...
0
votes
1answer
10 views

Compare text corpora

I have am currently performing speech recognition experiments on 2 different corpora. I have the ground truth human-labelled texts for both corpora. I am performing different experiments that lead to ...
0
votes
0answers
23 views

Choosing Gensim- Phrases parameters

I'm using the gensim.models.phrases in order to find bigrams in my data. For what I know,the main hyperparameters are: min_count and threshold. I have found ...
0
votes
0answers
20 views

Use mutual information score on multi label problem

I have a dataset in which each observation is assigned multiple topics, which also have a probability / confidence metric. I would like to evaluate my topic model using not just the top 1 assigned ...
1
vote
0answers
15 views

Auto scoring sales calls

I am not a statistician so pardon any incorrect technical term usage. I have learned just enough to know I don't know anything but am trying to understand the problem before engaging a real life ...
2
votes
1answer
32 views

Updating an unsupervised model but retaining similarity

In my example I am using topic modelling (specifically a version of LDA) although I think avenues for exploring this could relate to other unsupervised techniques like clustering. I train a model and ...
0
votes
1answer
60 views

Is there a way to get the optimal cutoff points based on probability of topic models and the outcomes?

I have topic models probability obtained using LDA topic models method. I’d like to use these probabilities for 5 topics to predict an ...
0
votes
0answers
20 views

Can you restrict the terms Latent Dirichlet Allocation(LDA) uses in specific topics?

I admit I do not have the full understanding of the inner-working of Latent-Dirichlet Allocation(LDA) yet. I have used the sklearn implementation on my text corpus. ...
0
votes
0answers
8 views

Predicting links between documents with topic models

I hope this is the right forum for this sort of question: I am trying to find a topic model that allows me to predict links between documents. Basically, I am trying to figure out if the topics in my ...
0
votes
0answers
27 views

Topic modelling when the “documents” are not static and new tokens are generated regularly

This question is related to this one and this one. As background, I'm working with Magic: the Gathering decklist data; I'm trying to automatically classify decks into different archetypes based on the ...
0
votes
0answers
18 views

Sentiment about topics (defined by LDA)

For a project I do a research about topics in online reviews, and the effect of these topics on the rating (by doing a regression). Furthermore and the reason I would like to have your help: I would ...
0
votes
0answers
23 views

Specify some words are not important and some words are extra important in topic modelling

I am using Latent Dirichlet Allocation in sklearn to model topics. I have a list of words that are likely to inform topics and a list of words that are not important (like stop words). Is there a way ...
0
votes
0answers
45 views

How does structural topic modeling's estimateEffect works?

I've been searching this for a while but haven't been able to find any information regarding how the STM's estimateEffect works. I'm reading the stm package ...
0
votes
0answers
25 views

Deriving Hyperparameter updates in Online Interactive Collaborative Filtering

I've been going through "Online Interactive Collaborative Filtering Using Multi-Armed Bandit with Dependent Arms" by Wang et al. and am unable to understand how the update equations for the ...
0
votes
0answers
8 views

Inference on Author model

The Author Model is an LDA based model that first time introduced in paper [The Author-Topic Model for Authors and Documents]. I have studied the inference of the LDA model and know how to obtain the ...
1
vote
0answers
17 views

Are 1-tailed 2-sample t tests suitable to assess if external validity performance is statistically significant better than a random model?

Some context: I currently have two groups of 50 text documents. Each group is about a different subject and curated by people. As such, I assume the two groups to be my ground truth. I mix the two ...
1
vote
0answers
36 views

parameter estimation on the LDA model

I have a problem with estimating the parameters of $\theta$, and $\phi$ in the Latent Dirichlet Allocation (LDA) model. The article Finding scientific topics has done the estimation of the parameters ...
1
vote
1answer
115 views

Can Latent Dirichlet Allocation (LDA) be used to generate word embeddings?

In the original Word2Vec paper (Efficient Estimation of Word Representations in Vector Space, Mikolov et al. 2013), I came across this phrase: Many different types of models were proposed for ...
0
votes
0answers
78 views

Interpreting the output of ldatuning and selecting the number of topics

I am conducting topic analysis using LDA and prior to specifying the topics, I wanted to determine the optimal number of topics statistically. I found the implementation in ldatuning to be very ...
0
votes
0answers
7 views

how would i find number of subtopic inside parent topic dynamically?

Here my objective is to create hierarchy of topic in such a way that sub topics for particular supertopic should represent the same context while it(subtopic) should be isolated with other children of ...
0
votes
0answers
9 views

Using individual documents for structural topic model or joining together small documents?

There has been a couple of other related questions about this posted but nothing exact. I'm using a structural topic model to model Twitter data (~5m tweets), the bulk of which were written in an 18m ...
0
votes
0answers
22 views

Thematic clustering of text

Please advise on starting points, research (papers,frameworks) related to thematic clustering of text. In particular on a system with two levels of clustering where second level has a temporal nature. ...
0
votes
0answers
12 views

Topic modeling/clustering using TF-IDF when adding real-time data

I’m clustering a collection of text documents (e.g., tweets) that are posted in a period of time, let’s say from a to b where <...
0
votes
0answers
24 views

Can I use LDA with 1 topic? I clustered my documents using doc2vec then DBSCAN. How can I visualize the topic of each cluster?

I did a doc2vec model then clustered the results using DBSCAN. Now that I have satisfactory results, how can I take these clusters into topics? Should i run LDA on each and make it give out 1 topic? ...
0
votes
0answers
41 views

Why in Latent Dirichlet Allocation perplexity is always best with maximum amount of topics?

I've build a Latent Dirichlet Allocation (LDA) model on 37,500 documents using the Java Mallet API. To automatically determine the "best" number of topics, I calculate the perplexity by splitting the ...
0
votes
1answer
64 views

LDA alpha equivalent in structural topic model

I'm using an implementation of the structural topic model (stm), written in R using the stm package. I want to reduce the number of topics that are prevalent in ...
0
votes
0answers
44 views

Why is my correlation matrix dropping that many NA?

I am trying to build a correlation matrix among documents per topic on a Latent Dirichlet Allocation model by text2vec, getting a doc_topic_distr matrix like below, with only first 5 documents, it's a ...
0
votes
1answer
65 views

How to intuitively interpret of topic distributions/coefficients in topic modeling

I know topic modeling such as LDA can provide the distribution of topics in documents, and the distribution of topics represent the important of that topic. However, I'm having a hard time intuitively ...

1
2 3 4 5 6