SAS Visual Text Analytics

Scale the human act of reading, organizing and extracting useful information from huge volumes of textual data.

Calibrate your LLM to improve outcomes with fit-to-task models

Manage toxicity, bias and bad actors to ensure trustworthy results. Improve data curation and minimize hallucinations by providing more relevant data to the LLM. Prevent private and sensitive data from entering the model by adding a layer of traceability.

Detect emerging trends & hidden opportunities

Quickly and tirelessly sift through growing volumes of text data to identify main ideas or topics, extract key terms, analyze sentiment, and identify correlations between words with the right combination of natural language processing, machine learning and deep learning methods, and linguistic rules. This helps get the right information to people when they need it.

Foster collaboration & information sharing in an open ecosystem

SAS Visual Text Analytics provides a flexible environment that supports the entire analytics life cycle – from data preparation, to discovering analytic insights, to putting models into production to realize value. Create, manage and share content, including best practice pipelines, in a highly collaborative workspace that easily integrates with existing systems and open source technology.

Improve analytics workflow with automation

Intelligent algorithms automatically detect relationships, topics and sentiment in text data, eliminating time-consuming manual analysis. Combine best-practice templates, automated rule generation and one-click model deployment to reduce model building efforts.

Key features

Augment human efforts to analyze unstructured text with AI using a variety of modeling approaches. Experience the combined power of natural language processing, machine learning and linguistic rules.

Large Language Model (LLM)-based classification

Use linguistic models to curate the best data for LLM fine-tuning and RAG. Augment LLM content moderation to detect toxicity and bias and prevent private data leakage to improve LLM outcomes without modifying or impacting the LLM.

LLM calibration

Use linguistic models to curate the best data for LLM fine-tuning and RAG. Augment LLM content moderation to detect toxicity and bias and prevent private data leakage to improve LLM outcomes without modifying or impacting the LLM.

Trend analysis

Unsupervised machine learning groups documents based on common themes. Relevance scores calculate how well each document belongs to each topic, and a binary flag shows topic membership above a given threshold.

Information extraction

Pull out specific pieces of information or relationships between information from text using a powerful, flexible and scalable SAS proprietary programming language called language interpretation for textual information (LITI).

Hybrid modeling approaches

Build effective text models using a variety of combined capabilities, including a rich mix of linguistic rules, natural language processing, machine learning and deep learning.

Parsing

Text is separated into words, phrases, punctuation marks and other elements of meaning to provide the human framework a machine needs to analyze text at scale.

Corpus analysis

Understand corpus structure through easily accessible output statistics to leverage natural language generation (NLG) for tasks such as data cleansing, separating out noise, sampling effectively, preparing data as input for further models (rules-based and machine learning), and strategizing modeling approaches.

Native support for 33 languages

Out-of-the-box NLP functionality enables native language analysis using dictionaries and linguistic assets created by native language experts from around the world.