Category Archives: Data Mining

02.11.14
by

Data Mining: Snapbird

Use:  find historical tweets to add context to or background for a news story

Snapbird is a free tool that allows you to search your own tweets or other users’ timelines for specific information.  In addition, you can search yours or other users’ favorites, tweets, mentions, direct messages you’ve sent and direct messages you’ve received. Select the search function, type in a Twitter username and a keyword, and Snapbird will list all messages that contain that keyword.

Previously, I wrote about Topsy, another Twitter search engine that allows you to search Twitter history by tweets, links, photos, videos and influencers.  But, unlike Snapbird, it does not allow you to search by specific Twitter user.

More:

journalism.co.uk: Tool for journalist: Snapbird, for searching Twitter

bloggingtips.com: Snap Bird: The Best Way to Search Beyond Twitter’s History

thenextweb: Snap Bird helps find old tweets and messages by going where Twitter Search can’t: months back

 

 

Advertisement
02.10.14
by

Social Media: Dataminr

Use:  Identifying newsworthy topics on Twitter

Dataminr is the latest tool for journalists to mine Twitter’s firehose of information for newsworthy leads.  I’ve shared on this blog other similar social media discovery tools , including NewsWhip Spike, Geofeedia, Facebook Conversations and CrowdyNews. (This site, although a bit dated, lists a range of news discovery tools and services).

Developed jointly with CNN and Twitter, Dataminr allows journalists to “set targeted alerts for certain types of breaking information that are then delivered automatically via application, email, pop-up, even instant message, depending on a user’s preference. Dataminr for News can be customized depending on a user’s particular topics of interest and regions of focus. Dataminr for News can also be directly integrated into existing internal client systems.”

The tool has not yet launched and no indication, yet, on when it will be available.

More:

re/code: Breaking News from Twitter: There’s Breaking News on Twitter

TechCrunch:  CNN And Twitter Partner With Dataminr To Create News Tool For Journalists

07.21.13
by

Data Mining: Google Survey

Use:  Create low-cost surveys for editorial content or to gain additional consumer insights

Google Survey allows publishers to create low-cost surveys on any topic they want.  Questions will be presented to users when they try to access certain premium content (from those publishers who are hosting Google Consumer Surveys on their paid content products).   Google  reports more than 200 publishers have implemented GCS.

Publishers present one question at a time and can segment the audience by gender, age, geography, urbanicity and income.  Unfortunately, the smallest geographic area is at the state level.  The question can be in a variety of formats, including single answer, multiple answers, side-by-side images, ratings and open-ended.  Publishers than choose number of responses per question (200, 500 or 1,000) and  frequency (once, biweekly, monthly).  Google charges $.10 per response for general population surveys and $.50 per response for segmented surveys.

According to Google, “Google Consumer Surveys takes a new approach to survey sampling, data collection and post-stratification weighting. This produces a close approximation to a random sample of the US Internet population and results that are as accurate as probability based panels.” A Google whitepaper on Google survey methodology and accuracy available here.

GCS may not replace more intensive consumer surveys for your publication, but could provide a low-cost approach to gaining specific insights more rapidly.

More:

TechCrunch: Google Surveys Can Make Anyone A Professional Pollster

Nieman Journalism Labs: The newsonomics of value exchange and Google Surveys

Forbes: Q&A With Paul McDonald: Co-Creator Of Google Consumer Surveys

 

07.03.13
by

Data Mining: Topsy

Use:  Increase engagement by surfacing relevant topics and conversations on Twitter; generate by helping ad customers target messages

Topsy is a tool that mines the full stream of Twitter tweets and, according to All Things D, “offers a set of professional analytics tools for sale, so that customers can find key data points like influential Twitter accounts, relevant content for specific time periods, even sentiment analysis around tweeted terms.”  There is also a free, limited tool at topsy.com.

News organizations can use the tool to identify topics and conversations that might suggest an interesting news story or possible story sources.  They can also use the tool to identify locally trending topics (e.g. “best lawn care tips”) that they can use to help local advertisers target promoted tweets.

Among the media organizations currently using Topsy are The New York Times, The Washington Post, ESPN, Gannett and ABC.

More:

All Things D: Data Analytics Startup Topsy Aims for the Local

 

06.03.13
by

Data Mining: Enigma

Use: Powerful tool for journalists to access and analyze publicly available data

Enigma (described as the “Google for public data”) sets out to “harmonize” publicly available data by providing tools to easily access millions of data points across thousands of diverse, public databases.   According to TechCrunch, the New York Startup (which won TechCrunch’s NY Disrupt competition and includes funding from The New York Times), “taps into over 100,000 public data sources from state and federal records to SEC filings to lists of frozen assets in the United Kingdom all the way to Crunchbase. The end result is an incredibly simple, incredibly smart way to sift through and find connections in publicly available data…”

They are now accepting requests for a free trial here.

More:
TechCrunch: Enigma makes unearthing and Sifting Through Public Data a Breeze
VentureBeat: Enigma brings the deep, dark world of public data to light
Datanami: Enigma.io Claims to Demystify Data; Receives Round