About TweetLevel
TweetLevel is a Twitter measurement tool created by @jonnybentwood at Edelman
This tool will be in permanent beta as we seek to continually improve its functionality
based upon your feedback. Even though we believe that it goes a great way to understand
and quantify the varying importance of different people's usage of Twitter, by no
means whatsoever do we believe we have fully solved the 'influence' problem. What
we would appreciate is your views, advice and criticism is crucial in helping us
understand social media measurement.
TweetLevel's Methodology
|
Fo
|
Number of followers
|
Fg
|
Number users following
|
|
Fo:Fg
|
Follower to Following ratio
|
Up
|
Number of updates all time
|
|
Updates over the past 30 days
|
|
Number of lists following you related to the number people following that list
|
|
Number of updates over specific time period
|
@U
|
Number of name pointing
|
|
Retweets related to quoted and edited proportioned to all time and previous 30 days
|
|
Replies sent related to all time and previous 30 days
|
|
B:E
|
Broadcast to engagement ratio
|
Is
|
Idea Starter score
|
|
To
|
Topsy influence score
|
Is
|
Involvement index score
|
|
Vi
|
Velocity index score
|
w
|
Weight assigned to each attribute
|
|
Z
|
Standardised score
|
p
|
Popularity
|
|
e
|
Engagement
|
i
|
Influence
|
|
t
|
Trust
|
Rg
|
Range assigned to score
|
Here's a bundle more info
Following
Twitter lists the number of people each user follows. The tendency for most celebrities
is to only follow a few individuals the more people that someone follows, there
is an increased likelihood of them actively participating in conversations with
the community instead of simply broadcasting to it. Following ranges were determined
(i.e. more than 20, more than 30, etc.) and each range was assigned a number (0
to 30) that was used as part of the algorithm. Note: Twitter opened its API to TweetLevel
so that data could be sourced easily and quickly to benefit the user.
Followers
Twitter lists the number of people each user follows. Some Twitter users do not
follow anyone but simply rely upon broadcasting what they have to say to all their
followers. Some parts of the algorithm place a higher weighting on being engaged
with a community and so following people is important but will not dramatically
change someones score. Following ranges were determined (i.e. more than 20, more
than 30, etc.) and each range was assigned a number (0 to 30) that was used as part
of the algorithm. Note: Twitter opened its API to TweetLevel so that data could
be sourced easily and quickly to benefit the user.
Updates
How often does someone update what they are doing. This number is purely objective
as it scores someone highly no matter what the content of their post (i.e. how relevant
is it). Nevertheless it is assumed that if someone posts frequently but has poor
content then their 'followers' will decrease. Additional factors such as their update
frequency over specific time periods and past 30 days were also used to calculate
a suers score. Update ranges were determined (i.e. more than 20, more than 30, etc.)
and each range was assigned a number (0 to 30) that was used as part of the algorithm.
Lists (quantity and following)
Twitter allows users to compile their own specific lists comprising up to 500 names
which other users can follow. TweetLevel analyses these lists and counts the number
of lists a user is included in and the number of people that follow these lists.
These numbers are aggregated and factored into the algorithm.
Name Pointing
e.g. @name How many people engage in conversation with an individual or point to
their name. The clearest way to establish this is to run a search on the number
of people who reference @username in a message. This calculation is based upon a
combination of factors looking back 12 days, 1500 tweets and activity over the past
24 hours. The number of times this happens is calculated with each range was assigned
a number (0 to 30) – again this was then used as part of the algorithm.
Replies
Working in association with ‘name pointing’, TweetLevel seeks to understand how
people engage with individuals via replying to them individually. The content and
time relationships of specific posts are analysed to understand how often someone
engages in conversation with an individual and replies to what they have said. The
number of times this happens is calculated with each range was assigned a number
(0 to 30) – again this was then used as part of the algorithm.
Retweets
Has a tweet caused sufficient interest that it is worth re-submitting by others?
Despite a great deal of 'noise' (i.e. posts that are not relevant or interesting),
when someone sees something that is of high interest, their post can be re-tweeted.
The clearest way to establish this is to run a search on the number of people who
reference RT @username in a message. This calculation is based upon a combination
of factors looking back 12 days, 1500 tweets and activity over the past 24 hours.
The number of times this happens is calculated with each range was assigned a number
(0 to 50) - again this was then used as part of the algorithm.
Broadcast to Engagement ratio
TweetLevel analyses the content of a users tweets to understand how much an individual
create engaging content as oppose to simply broadcasting their opinion. TweetLevel
rewards users that engage as oppose to merely create noise. The corresponding ratio
is calculated and each range was assigned a number (0 to 30) – again this was then
used as part of the algorithm.
Topsy Influence Rank
Topsy is an application that harvests all twitter data. This tool is also used to
replace Twitter’s search api that forced TweetLevel to temporarily close down whilst
the code was rewritten. This tool also has its own algorithm that measures influence.
By aggregating this data into TweetLevel, more confidence can be gained into calculating
a fair overall score. Similar to the other criteria, ranges were determined (i.e.
less than 20, less than 30, etc.) and each range was assigned a number (0 to 20)
that was used as part of the algorithm.
Idea Starter score
Whereas some people tend to pass on other peoples thoughts, others use twitter as
an amplification method of promoting their detailed observations – often via their
blog. TweetLevel takes this into consideration and rewards people accordingly for
originating detailed opinion and thought leadership. These scores are analysed and
entered into the algorithm.
Involvement Index
The Involvement Index is unique Edelman IP that calculates a score based upon how
an indivdual engages with their community. It is calculated by analysing the content
of an individual posts. People who score highest in this category have frequent,
relevant, high-quality content that actively involved the twitter community (asking
questions, posting links or commenting on discussions) and did not purely consist
of broadcasting. Ranges were determined (i.e. less than 20, less than 30, etc.)
and each range was assigned a number (0 to 20) that was used as part of the algorithm.
Velocity Index
As more people engage on Twitter, it may become harder to keep activity going. The
velocity index measures changes on a regular basis and assigns a score based on
increased or decreased participation. Ranges were determined (i.e. less than 20,
less than 30, etc.) and each range was assigned a number (0 to 20) that was used
as part of the algorithm.
Weighting
Each specific variable listed above was given a standard score out of 10. Using
a weighting scale I varied the importance of the each metric to establish an individual’s
total score.
Weighted for Popularity
The key variables are the number of people someone has following them as well as
the number of lists and their respective followers.
Weighted for Engagement
The key variables are an individual's participation with the Twitter community (as
measured by the Involvement Index), with additional emphasis on the frequency of
people name pointing an individual (via @username), the numbers of followers and
the broadcast to engagement ratio. Other attributes were included in the final score
but were given a lower weighting.
Weighted for Influence
The key variables in this instance is a combination of the number and authority
of someone's followers together with the frequency of people name pointing an individual
(via @username) and the how many times and individuals posts are re-tweeted – partially
calculated via the Idea Starter score. Other attributes were included in the final
score but were given a lower weighting.
Weighted for Trust
The best measure of trust is whether an in individual is will to ‘trust’ what someone
else has said sufficiently that they are also prepared to have what they tweeted
associated with them. The key metric in this instance looks at combination of retweets
and references (shown through 'via'. Other attributes were included in the final
score but were given a lower weighting.
