When we create a new audience, we follow a procedure to ensure that our clients are targeting the right audience. Please find below the list of steps that we follow when we create a new audience. Please keep in mind that the procedure may vary by audience.
- Social Database >> 700 million users
- Bio search
- Interests / passions / beliefs
- Statistically relevant accounts
- Gender & location algorithm
- Find Most Important People
- Word analysis
- Download current following
- Relevancy algorithm
- Find relevant influencers
- Download all followers
- Exclude irrelevant accounts
- Exclude other countries
- The community
- Apply filters and exclude waste
Example audience: Medical Oncologists.
We start with our Social Database, where 700 millon Social Media users are segmented and updated using multiple APIs. In this example, we start off with searching for the word ‘’Medical Oncologist’’ in Twitter bios. This search is based on self-reported data. Next, we download all accounts followed by these users. Then we remove statistically-irrelevant accounts and use our gender algorithm to define male/female/company/group accounts. After that, we look for the most relevant people based on our data, in this particular case ‘Medical Oncologists’. We also look for the most common words used by these oncologists in different languages. Then we download the most important accounts currently followed by the oncologists and we use our relevancy algorithm to define that. Once we have found the oncologist influencers, we download all followers of these influencers who are following more than for example 10 of these accounts. This number depends on the audience. In this case, we look at the most relevant number of accounts that is followed by real Medical Oncologists. After that, we exclude irrelevant accounts such as people with an inconsistent following behaviour and people from outside your target region. By now we have not only found the accounts based on self-reported data but also people who have the same following behaviour as an oncologist. The large majority of this audience will consist of real Medical Oncologists. However, in some cases the audience include other people who are not a Medical Oncologist even though they behave like one. In most cases, these people will be other Medical Professionals who work closely with Medical Oncologists. It is beneficial to include them in this audience as they will help us to get the message across. By targeting such a community however, we have a small risk of targeting patients in the unlikely event that a patient is behaving like a Medical Oncologist. Therefore, we exclude a list of words frequently used by patients such as patient, survivor, fighter and many more. Finally, we have created a global audience of patients based on keywords and behaviour. We exclude this audience in every campaign.
For privacy reasons, we will never share completed audiences in a way that user data is readable. Therefore we hash the data and we upload the hashed file into the Twitter Advertising accounts of our clients.
SHA-2 (Secure Hash Algorithm 2) is a set of cryptographic hash functions designed by the United States National Security Agency. Cryptographic hash functions are mathematical operations run on digital data; by comparing the computed "hash" (the output from execution of the algorithm) to a known and expected hash value, a person can determine the data's integrity. For example, computing the hash of a downloaded file and comparing the result to a previously published hash result can show whether the download has been modified or tampered with. A key aspect of cryptographic hash functions is their collision resistance: nobody should be able to find two different input values that result in the same hash output.