Tutorial
Introducing our cutting-edge TextWorker Google Sheet extension that gives you advanced Natural Language and Machine Learning/Artificial Intelligence power inside a standard spreadsheet environment. Tasks such as sifting, labelling, sentiment analysis, press-watching no longer need specialist teams developing custom applications – the people who understand the task can now solve it directly, with the tools already at their fingertips.
With our extension, you’ll be able to analyse and extract insights from your text data with the help of Natural Language Processing (NLP) techniques such as sentiment analysis, entity recognition, and keyword extraction using spreadsheet skills. These features enable you to quickly identify patterns, trends, and insights from your data; you do not need specialist coding skills, and your familiar spreadsheet work is extended without needing the support of specialist data science or AI teams.
Our extension also incorporates Machine Learning and Artificial Intelligence (ML/AI) capabilities, allowing you to train custom models that are tailored to your specific needs. By harnessing the power of ML/AI, you’ll be able to classify text data based on specific criteria, such as topic or sentiment, and quickly sift through large volumes of data to find the information you need.
Our extension is structured around the familiar and intuitive interface of the spreadsheet function – you really can get AI- and NLP-powered without coding skills. Simply install the extension, open your Google Sheet, and start exploring your data in new and exciting ways.
Overall, our Google Sheet extension is the perfect tool for anyone who wants to streamline their text processing and sifting workflow and uncover insights that might otherwise go unnoticed. Try it out today and see for yourself how it can transform the way you work with text data.
Classification Scoring with Multiple classification results
=nlp(“classifymulti”,reference_text,list_of_classifcations,max_num_results,”across”)
- reference_text = Input text
- list_of_classifcations =“software,hardware,networking”
- list_of_classifcations =“”, leave blank will automatically generate suggested classifications
- [optional] max_num_results= 2 will limit the number of results, useful if you have provide an extensive list of results
- [optional] Direction = “across | horizontal” Result score will appear across without labels
- Use only when a list of Known classifications is available
Example output (Classifications with Relevance Scores)
Example output when Direction is = “across” – scores only in the order of the list_of_classifcations provided
Classification Scoring with Single classification result
=nlp(“classify”,reference_text,list_of_classifcations)
- reference_text = Input text
- list_of_classifcations =“software,hardware,networking,Innovative”
Example output
Topics
=nlp(“topics”,reference_text,max_num_results)
- reference_text = Input text
- [optional] max_num_results= integer will limit the number of results, useful if you have provide an extensive list of results
Example output key topics
Example output of key topics limited to the top 5 (max_numbers=5)
Summarization
=nlp(“topics”,reference_text,compress_by_percentage)
- reference_text = Input text
- [optional] compress_by_percentage [1-100] will endeavor to compress the reference text by %
PROMPT
=nlp(“prompt”,prompt_text)
- prompt_text e.g. “What is the capital of peru ?”
Prompt – Simple Example
