strategic decision making with exploratory search toby mostyn cto polecat

Post on 31-Mar-2015

218 Views

Category:

Documents

0 Downloads

Preview:

Click to see full reader

TRANSCRIPT

Strategic decision making with exploratory search Toby Mostyn

CTO Polecat

Failing to meet the information need

Results: Finding “insights” in the noise

Queries: Handling complex topics

Solving both problems: an exploratory paradigm

What is the point of Polecat?

Darwinian algorithms

Agenda

What is the point of Polecat?

Intelligent searching

on

public conversations

Unlocking the Potential of Social Media!

Architecture

Searchplatform

News

Blogs

Social media

MeaningMine

Importer

Indexing

InformationExtraction

Failing to meet the information need

Results: Finding “insights” in the noise

Queries: Handling complex topics

Solving both problems: an exploratory paradigm

What is the point of Polecat?

Darwinian algorithms

Failing to meet the information need

What are the issues that people care about most?

Forming Policy

Give me an up to the minute / long-term info

on an issue

Issue Management

What/who is my product associated with?

Brand Management

I need to know,quickly,all about x

Briefing

Overview

Beyond traditional search

Irish Government: setting the agenda for the Irish Economic Forum

Query + results = failure to meet information need

Failing to meet the information need

Results: Finding “insights” in the noise

Queries: Handling complex topics

Solving both problems: an exploratory paradigm

What is the point of Polecat?

Darwinian algorithms

Queries: handling complex topics

Information need:

What is the discussion around innovation in the UK economy?

Simple keyword = failure

User unable to assess and select keywords

User unable to formulate complex boolean query

All (relevant) documents are important!

Queries: handling complex topics

Query by document

Feed in 1 to n documents

Pseudo relevance feedback

Query extraction -> query expansion

Exploratory interface

Results become query prompts

Users build iterative queries

Failing to meet the information need

Results: Finding “insights” in the noise

Queries: Handling complex topics

Solving both problems: an exploratory paradigm

What is the point of Polecat?

Darwinian algorithms

Results: Finding “insights” in the noise

Solution: Insights: extracted information/statistics that describe the data

Information Retrieval Statistics

Topic models

Sentiment analysis

Entity extraction Show me the data!

Goal: provide the user with an exploratory overview of the results

Results: Finding “insights” in the noise

Failing to meet the information need

Results: Finding “insights” in the noise

Queries: Handling complex topics

Solving both problems: an exploratory paradigm

What is the point of Polecat?

Darwinian algorithms

Solving both problems: an exploratory paradigm

Failing to meet the information need

Results: Finding “insights” in the noise

Queries: Handling complex topics

Solving both problems: an exploratory paradigm

What is the point of Polecat?

Darwinian algorithms

Darwinian algorithms

Polecat Ecosystem

Business

Academia

Darwinian algorithms Public search application: summarisation engine

Plug-in architecture for 3rd party algorithms/ visualisations

Crowd source judgements

Published evaluation tables (weekly/monthly)

Darwinian algorithms

Ranked insight by query type

Ranked insight combinations

Ranked visualisation by insight type

Individual scores for each contributor

Darwinian algorithms

top related