What is PYLON for LinkedIn Engagement Insights?

PYLON lets you build applications that analyze activities and events taking place on LinkedIn.

DataSift technology sits within the LinkedIn firewall. We receive an incoming stream of data from LinkedIn that includes activities and events performed by members on the network. These activities and events are stored into a large index, covering the last 30 days of activity.

Data is constantly recorded to the index in real-time, giving you an always available, always up-to-date 30 day history of LinkedIn activity to analyze.

What is LinkedIn Engagement Insights?

When a member or company posts a share, engages with a share, or clicks on a share on their LinkedIn newsfeed these interactions form the basis of LinkedIn Engagement Insights.

share-article

PYLON gives you access to these interactions for analysis through a privacy-first model that lets you build analysis results into your application.

LinkedIn Engagement Insights covers the following types of interactions on LinkedIn:

  • Members and companies sharing posts publicly.
  • Members and companies liking and commenting on posts, and resharing posts publicly.
  • Members and companies clicking on shares that appear in their newsfeed.
  • Members and companies clicking on articles authored by members on LinkedIn, or shared from other websites.

Every interaction includes details of links that were shared and the topic discussed. If an interaction was triggered by a member then the interaction includes demographic (age, gender, location, function and sector) details of the member.

These details are made available through targets and can be used both in analysis queries, and to drill-down into precise audience segments for detailed analysis.

note icon

Learn more about the data available from LinkedIn Engagement Insights:

In-depth analysis

PYLON for LinkedIn Engagement Insights gives you access to a rolling 30-day window of activities and events to analyze.

Currently PYLON supports two type of analysis results - time series and frequency distributions. There are a wide range of targets you can use for your analysis covering demographics, content and topics.

many-dimensions



When you submit a query you can specify a time window and also a filter (written in CSDL) to only analyze a subset of the index. For example you can specify only female members who work in healthcare, so analyze a very precise demographic. There are a wide range of targets you can use.

PYLON also supports nested analysis queries. With nested queries you can perform multiple-level analysis in one query that would otherwise take many analysis requests.

multi-dimension-analysis



By using query filters, nested queries and combining multiple query results you can build rich analysis results.

rich-analysis

note icon


Learn more about analysis queries and advanced analysis options:

Separating signal from noise

To truly understand your analysis results it is important to separate signal from the background noise, and reveal what is unique about your audience.

As the shared recording contains activies and events from all LinkedIn members, it is easy to compare your audience to a larger audience through 'baselining'.

This chart shows occupations engaging with cloud computing content (shown in blue), versus the general level of engagement for each occupation (shown in gray). You can see how technology-related occupations over-index for engagement in the topic.

baselined

Differences to PYLON for Facebook topic data

Note that PYLON for LinkedIn Engagement Insights uses the same technologies as PYLON for Facebook topic data, however the workflow is significantly different.

With PYLON for Facebook topic data:

  • You create an interaction filter that defines what data you'd like recorded to a private index.
  • You start a recording, waiting for data to fill your index.
  • You analyze the data recorded in your index.

With PYLON for LinkedIn Engagement Insights:

  • You access one shared index, containing all activities and events for the past 30 days.
  • DataSift ensure this index is constantly running and up-to-date.
  • You analyze the data recorded in the shared index.

Unlike Facebook for topic data, the LinkedIn implementation allows you to immediately explore activities and events, without needing to wait for a recording to fill with data. This allows you to explore, and iterate your solution rapidly.

Get started

With PYLON for LinkedIn Engagement Insights you can build rich analysis applications.

To get started with take a look at our Get Started page.