Dictionary weighted analysis, a capability has been used to assign weight to content for deeper analysis. As automation becomes more sophisticated so do the use cases. For example, HR has leveraged the capability of Dictionary Weighted Analysis to compare content differences between documents by assigning weights. Prior to automation, a collection of resumes took hours of HR human capital to review and compare resumes to find the best candidate. By creating a dictionary and assigning weight values to each term, HR automates the resume process and saves time. As a result, the best candidate is selected in an efficient manner.
The future of business is dictated by advancements in automation as it enhances human intelligence in different sectors of work. Technologies like Artificial Intelligence (AI), Natural Language Processing (NLP), and Machine Learning (ML) have redefined the way business is conducted by outsourcing redundant tasks to machines. As a result, more human ingenuity has been allotted to exploration and innovation.
Using Dictionary Weighted Analysis For Resume Analysis
Here is a detailed example of how the Content Analytics Platform (CAP) can be used for resume analysis. If you had 20 people apply for a project manager job, you can use CAP to rate the batch of resumes. Traditionally, recruiters looked at individual resumes to determine whether certain keywords integral to the job description were present. After highlighting keywords, the recruiters then scheduled an interview based on eligible resumes.
The Dictionary Weighted Analysis of the CAP can save your HR department the half a day it would take to go through 20 resumes manually. It saves the time of highlighting the words, keeping track of the number of times the word appears, and figuring out which words are important in each resume. If you set up the CAP with a dictionary that had not only keywords but synonyms and assign weights to the keywords, the CAP can analyze 20 resumes in 30 seconds.
The CAP would show you resumes in order of the number of times the words you were interested in appeared in the resume and show you the
same rank taking assigned weight into consideration. For example, hiring for a project manager, a “PMP” and project management professional can be set up as equal synonyms and given a high weight of 1.0. So, if you were looking at resumes, in order of importance you would look for a project manager who had a “PMP” as a “must have” for the job. Then, you could assign a much lower weight of .5 for a “nice to haves” keyword such as “scrum” or “agile certification”. Also, you could also set up CSM (certified scrum master) as a synonym for an agile certified practitioner (ACP). Similarly, a “nice to have” keyword in a project manager resume such as – “business analysis” could have “BA” with an assigned weight of .2.
(Suggest using Janson’s updated Resume Comparison template containing bar charts as an image in this blog).
Why Does Dictionary Weighted Analysis Matter?
Dictionary Weighted Analysis helps businesses make smart decisions. Smart decisions are more precise due to being data driven rather than based on guesswork. Dictionary Weighted Analysis provides the ability to capture important and critical textual content in unstructured data. Unstructured data was previously inaccessible to businesses because it was difficult to access and mine. In the HR example, Dictionary Weighted Analysis removes human error and bias in analyzing resumes. It is also sensitive to how important certain terms are to the business. Weights range from 0 to 1.0, at the hundredth level (e.g., .55). Typically, the greater weight, the higher the importance. This can be used in either a positive or negative aspect. A positive aspect is scanning resumes for skills with the “must-haves” having the weight of 1.0, while the “nice-to-haves” are .25. The negative is the inverse of the positive, such as identifying high and low risks.
Scion Analytics empowers users of the Content Analytics Platform (CAP) to imagine what they can do with the platform. Scion Analytics’ Dictionary Weighted Analysis creates flexible dictionaries and provides deeper analysis for content. The capabilities of the platform can be quickly customized to fit business needs. A common use case is the Bid/No Bid requirement analysis, determining the requirements to a company’s capability and identifying risks associated with these requirements. Also, Dictionary Weighted Analysis can be used to identify risks in an agreement, contract, and Request for Proposal (RFP). It could also be used to identify
words and phrases that should not be used in company documents such as proposals.
Our users have developed other use cases for using weighted terms that we never imagined.
If the future of work belongs to intelligent automation, it is content analytics tools like the CAP and capabilities like Dictionary Weighted Analysis that are examples of new opportunities to come.