Word Clouds for Job Search
Job search is a very fascinating and interesting occupation. But sometimes it gets tiresome. A lot of monotonous text and your eyes can’t catch any point anymore. People like to work with visually appealing data, when job descriptions usually look like a monolite piece and all words merge together. When it happens you can’t efficiently update your job search toolkit– your resume and cover letter. After it happened with me I started to research how to make my job search enjoyable.
I found that word clouds can be part of a job search and exercise to improve Data Science skills in mining text and NLP (Natural Language Processing), they will help you refine your toolkit and support job search success.
Text mining methods allow us to highlight the most frequently used keywords in a paragraph of texts, we deriving the most meaningful information from text.
NLP — Natural Language Processing — helps to interact between computers and humans using the natural language.
Customized cover letters and resumes help hiring managers to find you faster among all applicants. Keywords in a resume that match the keywords in a job description increases the chance of being invited for an interview.
Right message to everyone!
If you’ve found a job you are interested in applying for, begin by creating a word cloud from the employer’s job description.
Word Cloud is a data visualization technique. In which words from a given text display on the main chart. In this technique, more frequent or essential words display in a larger and bolder font, while less frequent or essential words display in smaller or thinner fonts. It is a beneficial technique in NLP that gives us a glance at what text should be analyzed.
Why can word clouds be useful?
The cloud I go to build is a word cloud containing key information for job seekers. Thus I can make better strategies based on what I see on the cloud.
For simple exercise with Python I going through the next steps:
- Found a job I am interested in applying for
- Save description for this job position in text file
- Split text from file into words
- Use TF-IDF to weight the importance of words
- Generate a word cloud using outputs from step four
TF-IDF is a numerical statistic that is intended to reflect how important a word is to a document in a collection or corpus.
For step 1 you can use any job-board site or career section on a company’s website. Copying and pasting into the test file job description is very simple. For future work I think about web scraping techniques to get job information from sites. But it can not be that easy task because all sites have different layouts.
When I have a file for work, I can create word clouds immediately. Unfortunately, such a presentation of information does not carry any semantic meaning, it simply translates the text into an image.
For better understanding what I see, I should go to the next step and split text:
- In order to remove redundancies convert the whole of the text to lower case.
- Remove stop words to avoid counting meaningless words.
- Remove common words found from job details like “may”, “must”, “position”, etc..
- Transform the job detail through TF-IDF model and pick the top 500 weighted words.
Finally, after all transformation and cleaning I have all required data and ready to generate a word cloud.
This world cloud can help to focus what else is needed for my resume and cover letter. I can clearly see all key skills.
Summary
Word clouds will help you identify keywords and skills within your target job description. It is good for optimizing your resume, profiles and cover letters since you can’t tailor your profile to a single job description.
