保留正文与补采附件。源页面当前未重新核验；具体限制见交付清单。

Revisit consent button We value your privacy We use cookies to enhance your browsing experience, serve personalised ads or content, and analyse our traffic. By clicking "Accept All", you consent to our use of cookies. Customise Reject All Accept All Customise Consent Preferences We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below. The cookies that are categorised as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... Show more NecessaryAlways Active Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

Functional Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

Analytics Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

Performance Performance cookies are used to understand and analyse the key performance indexes of the website which helps in delivering a better user experience for the visitors.

Advertisement Advertisement cookies are used to provide visitors with customised advertisements based on the pages you visited previously and to analyse the effectiveness of the ad campaigns.

Uncategorised Other uncategorised cookies are those that are being analysed and have not been classified into a category as yet. No cookies to display. Reject All Save My Preferences Accept All Toggle SearchToggle Mobile Navigation Publish AI, ML & data-science insights to a global community of data professionals. Sign inSubmit an Article LatestEditor's PicksNewsletterShipAI

Write For TDS LinkedInXToggle Search Large Language Models

Topic Model Labelling with LLMs

Python tutorial for reproducible labeling of cutting-edge topic models with GPT4-o-mini. Petr Koráb July 14, 20256 min read Image by authors By : Petr Koráb , _Martin Feldkircher*, *** Viktoriya Teliha_ ** (*Text Mining Stories, Prague, **Vienna School of International Studies, ***Centre for Applied Macroeconomic Analysis, Australia). Manual labeling of terms produced by topic models requires domain experience and may be subjective to the labeler. Especially when the number of topics grows large, it might be convenient to assign human-readable names to topics automatically with an LLM. Simply copying and pasting the results into UIs, such as chatgpt.com, is quite a “black-box” and unsystematic. A better choice would be to add topic labeling to the code with a documented labeler, which gives the engineer more control over the results and ensures reproducibility. This tutorial will explore in detail:

We will train a cutting-edge FASTopic model by [Xiaobao Wu et al. 3] presented at last year’s NeurIPS. This model outperforms other competing models, such as BERTopic , in several key metrics (e.g., topic diversity) and has broad applications in business intelligence. Learn this step by step with the interactive AI Engineer roadmap.

1. Components of the Topic Modelling Pipeline

Labelling is the essential part of the topic modelling pipeline because it bridges the model outputs with real-world decisions. The model assigns a number to each topic, but a business decision relies on the human-readable text label summarizing the typical terms in each topic. The models are typically labelled by (1) labellers with the domain experience, often using a well-defined labelling strategy, (2) LLMs, and (3) commercial tools. The path from raw data to decision-making through a topic model is nicely explained in Image 1. Image 1. Components of the topic modeling pipeline.
Source: adapted and extended from Kardos et al [2]. The pipeline starts with raw data, which is preprocessed and vectorized for the topic model. The model returns topics named with integers, including typical terms (words or bigrams). The labeling layer replaces the integer in the topic name with the text label. The model user (product manager, customer care dept., etc.) then works with labelled terms to make data-informed decisions. In the following modeling example, we will follow it step by step.

2. Data

We will use FASTopic to classify customer complaints data into 10 topics. The example use case uses a synthetically generated Customer Care Email dataset available on Kaggle, licensed under the GPL-3 license. The prefiltered data covers 692 incoming emails to the customer care department and looks like this: Image 2. Customer Care Email dataset. Image by authors.

2.1. Data preprocessing

Text data is sequentially preprocessed in six steps. Numbers are removed first, followed by emojis. English stopwords are removed afterward, followed by punctuation. Additional tokens (such as company and person names) are removed in the next step before lemmatization. Read more on text preprocessing for topic models in our previous tutorial. First, we read the clean data and tokenize the dataset: python

import pandas as pd

# Read data
data = pd.read_csv("data.csv", usecols=['message_clean'])

# Create corpus list
docs = data["message_clean"].tolist()

Image 3. Recommended cleaning pipeline for topic models. Image by authors.

2.2. Bigram vectorization

Next, we create a bigram tokenizer to process tokens as bigrams during the model training. Bigram models provide more relevant information and identify better key qualities and problems for business decisions than single-word models (“delivery” vs. “poor delivery”, “stomach” vs. “sensitive stomach”, etc.). python

from sklearn.feature_extraction.text import CountVectorizer

bigram_vectorizer = CountVectorizer(
    ngram_range=(2, 2),               # only bigrams
    max_features=1000                 # top 1000 bigrams by frequency
)

3. Model training

The FASTopic model is currently implemented in two Python packages:

We will use the Turftopic implementation because of the direct link between the model and the Namer that offers LLM labelling. Let’s set up the model and fit it to the data. It is essential to set a random state to secure training reproducibility. python

from turftopic import FASTopic

# Model specification
topic_size  = 10
model = FASTopic(n_components = topic_size,       # train for 10 topics
                 vectorizer = bigram_vectorizer,  # generate bigrams in topics
                 random_state = 32).fit(docs)     # set random state 

# Fit model to corpus
topic_data = model.prepare_topic_data(docs)

Now, let's prepare a dataframe with topic IDs and the top 10 bigrams with the highest probability received from the model (code is here). Image 4. Unlabeled topics in FASTopic. Image by authors.

4. Topic labeling

In the next step, we add text labels to the topic IDs with GPT4-o-mini. Let’s follow these steps:

With this code, we label the topics and add a new row topic_name to the dataframe. python

from turftopic.namers import OpenAITopicNamer
import os

# OpenAI API key key to access GPT-4
os.environ["OPENAI_API_KEY"] = ""   

# use Namer to label topic model with LLM
namer = OpenAITopicNamer("gpt-4o-mini")
model.rename_topics(namer)

# create a dataframe with labelled topics
topics_df = model.topics_df()
topics_df.columns = ['topic_id', 'topic_name', 'topic_words']

# split and explode
topics_df['topic_word'] = topics_df['topic_words'].str.split(',')
topics_df = topics_df.explode('topic_word')
topics_df['topic_word'] = topics_df['topic_word'].str.strip()

# add a rank for each word within a topic
topics_df['word_rank'] = topics_df.groupby('topic_id').cumcount() + 1

# pivot to wide format
wide = topics_df.pivot(index='word_rank', 
                       columns=['topic_id', 'topic_name'], values='topic_word')

Here is the table with labeled topics after additional transformations. It would be interesting to compare the LLM results with those of a company insider who is familiar with the company's processes and customer base. The dataset is synthetic, so let’s rely on the GPT-4 labeling. Image 5. Labeled topics in FASTopic by GPT4–o-mini. Image by authors. We can also visualize the labeled topics for a better presentation. The code for the bigram word cloud visualization, generated from the topics produced by the model, is here. Image 6. Word cloud visualization of labeled topics by GPT4–o-mini. Image by authors.

Summary

The data and complete code for this tutorial are here. Petr Korab is a Senior Data Analyst and Founder of Text Mining Stories with over eight years of experience in Business Intelligence and NLP. Sign up for our blog to get the latest news from the NLP industry!

References

[1] Feldkircher, M., Korab, P., Teliha, V., (2025).“What Do Central Bankers Talk About? Evidence From the BIS Archive,” CAMA Working Papers 2025–35, Centre for Applied Macroeconomic Analysis, Crawford School of Public Policy, The Australian National University. [2] Kardos, M., Enevoldsen, K. C., Kostkan, J., Kristensen-McLachlan, R. D., Rocca, R. (2025). Turftopic: Topic Modelling with Contextual Representations from Sentence Transformers. Journal of Open Source Software , 10(111), 8183, https://doi.org/10.21105/joss.08183. [3] Wu, X, Nguyen, T., Ce Zhang, D., Yang Wang, W., Luu, A. T. (2024). FASTopic: A Fast, Adaptive, Stable, and Transferable Topic Modeling Paradigm. arXiv preprint: 2405.17978.

Register Now to Continue Reading

Unlock Towards Data Science with a Free Account

All articles on Towards Data Science are available to registered users. Create a free account today to access this article and thousands more. Register for freeSign in to your account

Written By

Petr Koráb

See all from Petr Koráb LlmMachine LearningNLPPythonTopic Modeling Share This Article

Towards Data Science is a community publication. Submit your insights to reach our global audience and earn through the TDS Author Payment Program. Write for TDS

Related Articles

I Combined the Blockchain and AI to Generate Art. Here's What Happened Next.

Large Language Models Using LLMs to create artistic representations of data Kory Becker December 30, 20247 min read

The Magic of Quantum Computing: A Beginner's Guide to Writing a Magic Number Guessing Game

Game Development Programming a quantum computer is fun! Kory Becker February 10, 20239 min read

How to Fine-Tune Llama2 for Python Coding on Consumer Hardware

Large Language Models Enhancing Llama2's proficiency in Python through supervised fine-tuning and low-rank adaptation techniques Luís Roque August 17, 202320 min read

Impute Dates in a Pandas DataFrame with Lambdas

Programming Have wacky dates in your data? Instead of dropping or filtering them, impute or substitute them with a reasonable, best-guess. Justin Chae December 30, 20208 min read

Reinforcement Learning, Part 6: n-step Bootstrapping

Artificial Intelligence Pushing the boundaries: generalizing temporal difference algorithms Slava Efimov August 7, 20246 min read

The Large Language Model Course

Artificial Intelligence How to become an LLM Scientist or Engineer from scratch Maxime Labonne January 16, 202518 min read

3 underrated strategies to deal with Missing Values

Artificial Intelligence Implement, understand and learn about how 3 powerful methods, including Deep Learning, can be used to impute data. Vagif Aliyev October 30, 20209 min read

New Insights on the Power of Graphs

Machine Learning Our weekly selection of must-read Editors' Picks and original features TDS Editors May 5, 20223 min read

Talk to my Agent

Artificial Intelligence The exciting new world of designing conversation driven APIs for LLMs Roni Dover July 28, 20258 min read

Your home for data science and AI. The world's leading publication for data science, data analytics, data engineering, machine learning, and artificial intelligence professionals. Subscribe to Our NewsletterWrite For TDS•About•Advertise•Privacy Policy•Terms of Use © Insight Media Group, LLC 2026•The New Stack•roadmap.sh•Creator Network

Recommended Articles

Close