SenTop

SenTop combines sentiment analysis and topic modeling into a single capability allowing for sentiments to be derived per topic and for topics to be derived per sentiment.

Installation

To install with pypi, use:

pip install sentop

Quick Start

Create a SenTop object and pass your list of documents to run_analysis().

st = SenTop()
st.run_analysis(docs, annotation="My dataset")

Sentiment Analysis

Sentiment analysis is performed using AdaptNLP with state-of-the-art (SOTA) Hugging Face Transformers. SenTop provides multiple sentiment analyses (confidence scores also available):

1. RoBERTa Base Sentiment for 3-class sentiment -- based on Facebook AI's RoBERTa
2. BERT Base Multilingual Uncased Sentiment for 5-class sentiment -- based on Google's Bidirectional Encoder Representations from Transformers (BERT)
3. Twitter roBERTa-base for Emotion Recognition for 4-class emotion recognition
4. BERT-base-cased Geomotions (Original) for 28-class emotion recognition
5. Twitter roBERTa-base for Offensive Language Identification for 2-class offensive language detection

Topic Modeling

SenTop provides two types of topic modeling: Latent Dirichlet Allocation (LDA) using Tomotopy and transformer-based BERTopic. While LDA provides de facto, statistical-based topic modeling, BERTopic provides SOTA-level performance using Hugging Face Transformers. Transformers that have been tested include:

1. BERT Base Uncased -- based on Google's Bidirectional Encoder Representations from Transformers (BERT)
2. XLM RoBERTa Base -- based on XLM-RoBERTa

Combining Sentiment Analysis and Topic Modeling

SenTop combines sentiment analysis and topic modeling by copmuting both at the document level for a corpus, the results of which can then be represented by a table as shown below.