ixp
latest
false
- 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
Important :
Communications Mining is now part of UiPath IXP. Check the Introduction in the Overview Guide for more details.
Communications Mining user guide
Last updated Aug 1, 2025
Creating a dataset
Note: You must have assigned the Dataset - Manage permission as
an Automation Cloud™ user, or the Modify datasets permission as a legacy user to
create datasets.
To create a dataset, access IXP, select Create dataset from the main page, and continue with the following steps:
Name and source
- Fill in the required fields:
- Dataset Name - Enter the name of the dataset.
- API Name - Enter a descriptive name for your dataset using hyphens instead of spaces. For example, zendesk-cs-chats.
- Project - You can:
- Select an existing project from the dropdown menu where the dataset should be added. You can assign the dataset to any of the projects that you are a member of.
- Select Create new to create a new project, fill in the Title and Name fields, and select Save.
Note: To create a new project, you must have assigned the Tenant - Manage permission as an Automation Clud user, or the Tenant Admin permission as legacy user. - Use generative AI features - Use the toggle to enable or disable this
option. The features provide design-time and run-time capabilities, which
use third-party generative AI models. These significantly improve time to
value with features such as Generative annotation.
If you use the preview generative extraction mode, this uses a third-party LLM, and requires you to turn on the toggle for Use preview generative extraction model.
Note: To disable third-party LLMs, make sure you turn off the Use Generative AI Features toggle for a dataset. - Sources - Configure one of the following options:
- Existing source - Select an existing source from the dropdown list.
- New source -
- Source Name - Enter the name of the source.
- API Name - Enter the API name for the source. Once
added, you cannot change the API name.
Note: To add a new source, you must have assigned the Source - Manage permission as an Automation Cloud™ user, or the Source Admin permission as a legacy user.
- Model language - Select the model language that matches the language
of your data:
- English
- Multilingual model - For more details, check Multilingual sources and datasets.
- Select Next to continue to the Define labels page.
Define labels
- Select Add label to add one or multiple labels.
- Select Import labels, and select one of the following options from the
dropdown menu:
- Copy from spreadsheet
- Import from a dataset - Copies labels and descriptions only from an existing dataset. To copy an entire dataset, select Duplicate from the Datasets.
- Select Next to continue to the Additional settings page.
Additional settings
- Configure one or all of the following options:
- Quality of service - When enabling this option, it automatically enables Tone Analysis and the Pretrained QoS labels.
- Pretrained QoS labels - Add any pre-trained labels to your dataset. Some examples could include chaser, urgent, out of office, and so on. You do not have to enable any during the dataset creation. You can always enable them later in the dataset settings page.
- Tone Analysis - Enable or disable tone analysis to understand the intent behind communication.
- Label sentiment - Enable or disable sentiment analysis. When you enable this option, every label in the taxonomy has an associated positive or negative sentiment. For more details, check Enabling sentiment on a dataset.
- Select Create to create the dataset.
Note:
- You can add up to 20 individual sources to a dataset in the GUI.
- Sources can sit in a different project to a dataset. As long as you have the appropriate permissions in each project, you can view the messages, and annotate as usual.
- If there are multiple sources in a dataset, they should share a similar intended purpose for your analysis.
