- Introduction
- Setting up your account
- Balance
- Clusters
- Concept drift
- Coverage
- Datasets
- General fields
- Labels (predictions, confidence levels, label hierarchy, and label sentiment)
- Models
- Streams
- Model Rating
- Projects
- Precision
- Recall
- Annotated and unannotated messages
- Extraction Fields
- Sources
- Taxonomies
- Training
- True and false positive and negative predictions
- Validation
- Messages
- Access Control and Administration
- Manage sources and datasets
- Understanding the data structure and permissions
- Creating or deleting a data source in the GUI
- Uploading a CSV file into a source
- Preparing data for .CSV upload
- Creating a dataset
- Multilingual sources and datasets
- Enabling sentiment on a dataset
- Amending dataset settings
- Deleting a message
- Deleting a dataset
- Exporting a dataset
- Using Exchange integrations
- Model training and maintenance
- Understanding labels, general fields, and metadata
- Label hierarchy and best practices
- Comparing analytics and automation use cases
- Turning your objectives into labels
- Overview of the model training process
- Generative Annotation
- Dastaset status
- Model training and annotating best practice
- Training with label sentiment analysis enabled
- Training chat and calls data
- Understanding data requirements
- Train
- Introduction to Refine
- Precision and recall explained
- Precision and Recall
- How validation works
- Understanding and improving model performance
- Reasons for label low average precision
- Training using Check label and Missed label
- Training using Teach label (Refine)
- Training using Search (Refine)
- Understanding and increasing coverage
- Improving Balance and using Rebalance
- When to stop training your model
- Using general fields
- Generative extraction
- Using analytics and monitoring
- Automations and Communications Mining™
- Developer
- Exchange Integration with Azure service user
- Exchange Integration with Azure Application Authentication
- Exchange Integration with Azure Application Authentication and Graph
- Fetching data for Tableau with Python
- Elasticsearch integration
- Self-hosted Exchange integration
- UiPath® Automation Framework
- UiPath® Marketplace activities
- UiPath® official activities
- How machines learn to understand words: a guide to embeddings in NLP
- Prompt-based learning with Transformers
- Efficient Transformers II: knowledge distillation & fine-tuning
- Efficient Transformers I: attention mechanisms
- Deep hierarchical unsupervised intent modelling: getting value without training data
- Fixing annotating bias with Communications Mining™
- Active learning: better ML models in less time
- It's all in the numbers - assessing model performance with metrics
- Why model validation is important
- Comparing Communications Mining™ and Google AutoML for conversational data intelligence
- Licensing
- FAQs and more
Communications Mining user guide
verbatim(s) changed to messages.
A message is what we call a single unit of free-form text communication, such as an email, a survey response, a note, a chat, or a phone call transcript. Messages are grouped together in sources.
The following image contains an example of how a message is presented in the Explore page of the user interface.
Every message has associated metadata that consists of structured data points that provide additional information about the communication or conversation and its participants.
All messages are required to have an associated timestamp, which typically corresponds to the time at which that message was originally created.
In addition to timestamps, the platform typically stores additional metadata associated with each message. Typical examples of metadata fields are:
- Name and contact details of the message participants.
- Sender and receiver domains for emails.
- Number of messages in a chat conversation or number of emails in a thread.
- Demographical data, such as gender, age, country, and so on.
- A quantitative measure of customer satisfaction with the interaction, such as Net Promoter Score (NPS), Customer Satisfaction Score (CSAT), and so on.
- For phone calls, the raw audio the platform used to transcribe it.
- Third-party IDs used when the Messages are imported from another system, for example, the email message ID from an Exchange server.
Some datasets may contain messages with PII (personally identifiable information) in their metadata, such as userId. Therefore, you can mark these fields as sensitive. By marking these fields as sensitive, viewing this metadata requires enhanced user permissions.
Having rich message metadata allows users greater ability to train and analyze their data within the platform, as users can filter by metadata fields within both the Explore and Reports pages.
