2. Resume Screening Process
• Screening resumes is an important part of the
selection process.
• There are many aspects to consider when
screening resumes, such as the appearance
and organization of the resume as well as the
job responsibilities listed.
3.
4. The screening Process
6 main factors evaluator should keep in mind while
reviewing the process
• Job relevance - Compare the job description and qualifications desired for
the vacant position against the applicant's resume, noting the similarities
with the person’s past positions and responsibilities.
• Picture the position - Spot how each candidate can fit in the desired
position. .g. what candidate is currently working, culture of the
organization, and general work setting.
• Do not draw conclusions - Resumes can be misleading. E.g. if candidate
attended an university does not mean that they actually graduated, unless
award of a degree is clearly stated .
5. • Watch for misleading information — e.g. a candidate who
does not list dates of employment may be trying to conceal
a period of unemployment. Likewise, an applicant who
focuses too much on hobbies and not enough on job
responsibilities may be trying to compensate for an
insufficient amount of work experience or lack of
professional preparation.
• Ignore any discriminatory information
• Sourcer should be reasonable and impartial — Should not
fall for appearance of the resume, hobbies of the
candidate, or organizational affiliations.
6. Reviewing individual resumes
• “By evaluating all candidates against the same screening standards,
. . . [the]
• process will be more objective, fair and accurate”.
• + Evaluator should set list of standards and criteria to compare
resumes
• + Job description and any other relevant information should also be
• compared with resume
• + Standards should not be bend, as they were created to meet the
job
7. Technologies to be used
• 1. Software requirement :
• i. Jypeter notebook
• ii, Colab
• 2. Technology used
• i. NLP
• ii. Python
• iii, Spacy tool
10. spaCy
• We use python’s spaCy module for training
the NER model.
• spaCy’s models are statistical and every
“decision” they make — for example, which
part-of-speech tag to assign, or whether a
word is a named entity — is a prediction.
• This prediction is based on the examples the
model has seen during training,
11. Resume Summarization using NER
• Data preparation: Our first task is to create
manually annotated training data to train the
model.
(1136, 1248, ‘Skills'),
(928, 932, ‘Graduation Year’),
(858, 889, ‘College Name"),
(821, 856, "Degree’),
(787, 791, ‘Graduation Year"),
(744, 758, ‘Companies worked at’),
(722, 742, ‘Designation'),
12. • PDF to TXT: Our aim for this project is to
come up with an end-to-end tool which
takes in a document and gives out the
expected result, in this case - The category
and the summary.
13. • Data Cleaning:
• Unnecessary separators: A lot of resumes had separators like a string of ’-’, which
was
• considered to be removed too
• Punctuation and Stop Words: Punctuation and stop words didn’t seem to add any
value
• to the analysis, and hence it was decided to be gotten rid of.
• Erroneous Formatting: There were also some records with highly erroneous
formatting
• which came in the way of our cleaning/analysis. Getting rid of them was the best
resort.
• Personal details: Details like email id, phone numbers, dates ete would add
nothing but
• plain noise to the analysis which would add merely any value in the process of
classification.It was hence considered best to remove them.
14. Conclusion
Screening resumes is a time consuming but an important part of the
selection
process.
In this phase of the staffing process one should be carefully organized
and
guided by application of the standards of professional ethics and legal
constraints concerning discrimination.
How well these tasks are accomplished directly affect the ultimate
quality of
staff employed in the Organization.