Boolean Recruiting Tips

It’s official.

The SourceCon event at the Georgia Aquarium on Feb 9 & 10 will be the biggest event ever, with more attendees than any other SourceCon!

What that really means, other than proof that Atlanta is the center of the sourcing universe [sorry Seattle ], is that attendees will have more opportunity to network with, share best practices, and learn from other sourcers and sourcing leaders than ever before.

As you would expect, SourceCon will treat those in attendance with high-value keynotes and general sessions from industry luminaries such as:

• Aida La Chaux from Yahoo on sourcing through adversity
• Adam Lawrence of Alexander Mann Solutions on global sourcing
• Jim Stroud of Bernard Hodes on social & personalized search
• Eric Jaquith from SourceRight on how to stack the deck in your favor when it comes to sourcing
• Conni LaDouceur on phone sourcing best practices (and yes, you’ll hear recorded calls!)

In addition, there are breakout tracks for sourcing leaders and for sourcing practitioners lead by Charles Bretz, Shannon Van Curen, Shannon Myers, Cathy Henesey, Elaine Order, Justin Clem, Anne DeWys, Therese Hightower, Cathy Henesey, and Atlanta’s own Chris Havrilla, covering topics such as ATS/candidate databases and social and mobile sourcing.

So what will I be doing there?

Well, this will be my 5th SourceCon, and instead of presenting a keynote, I am honored to be the official Conference Chair, so I will be leading off the event, facilitating discussions, and wrapping up each day.

When I kick off the event, I plan to address the current state of sourcing and what I believe to be the future of sourcing.

I also plan to bring up the recent Sourcing Compensation Survey which has some fantastic data, and an excellent infographic.

Register for SourceCon

There’s still time to register and attend – and you can take advantage of my special discount code (find it in the image above) to save 10%.

If you’re local or can get to Atlanta by Thursday – you won’t want to miss this sourcing event!

For a while, there was an interesting little method for revealing the full name of 3rd degree and group connections on LinkedIn. However, LinkedIn has changed the “get introduced” functionality and UI for most people and effectively eliminated that method (albeit unintentionally, IMO).

Oh well – it was easy and fun while it lasted.

Fortunately, I’ve recently become aware of another way of revealing the full names of 3rd degree connections on LinkedIn with a less-than-premium account that I would like to share with you.

But before we get to that, I’d like to cover some basics as well as some things I have been noticing about LinkedIn – I believe they may be tinkering with free access profile visibility.

Oh, and if you’re on the fence about attending SourceCon in Atlanta next week, it’s shaping up to be the largest in SourceCon history, and you still have time to register and get a 10% discount using my SC12GC code.

LinkedIn Public Profile Search to View Full Names

Now that the nifty “get introduced” full name visibility trick is seemingly dead, people without LinkedIn Recruiter access can of course still grab one or more unique phrases from 3rd degree and group-only LinkedIn connections and throw them into Bing or Google to find their public profile and thus their full names.

For example, I can take the headline phrase and couple it with the location phrase from a LinkedIn search result…

 

 

…and enter this into Bing: “Senior Software Development Manager, IBM” “Ottawa, Canada Area”, and here’s what I get:

 

 

You can do the same thing with Google, but Google’s first result isn’t the profile we’re looking for – that’s why I favor Bing for this technique. Google seems to index all of the nooks and crannies of LinkedIn yielding “dirty” and irrelevant results when searching for LinkedIn profile word/phrase combinations.

Is LinkedIn Tinkering with Public Profile Visibility?

I am sure I am not alone in noticing changes to the standard LinkedIn X-Ray search results.

For example, while you could see the full names of 3rd degree and group-only connections after clicking on a search result even if you were logged into LinkedIn, now I am finding that if I am logged in, once I click on a Google or Bing LinkedIn site: search result, LinkedIn recognizes that I am not connected to the person at the 1st or 2nd degree and thus only shows me the first name and last name initial.

Here is a screenshot of my Google search and the result – the full name is displayed:

 

 

However, once I click on the search result, if I am logged into LinkedIn, I only see the first name:

 

 

I know for a fact this has not always the case – I’ve been training people on this for years and I’ve done this 1,000′s of times.

Big deal?

No – but I still find it interesting to notice changes like this because it means what we have all been wondering about (fearing?) may finally be coming – evidence that LinkedIn is working to limit or close off free access to LinkedIn data.

In fact, I’ve also been running into some seemingly random funny business with LinkedIn public profile URL’s. I have encountered a number of instances in which I’m using either Chrome or IE and I click on (or cut and paste) a public profile link, LinkedIn tells me that the profile is not found, when I know it does exist because I just looked at it.

For example here’s one I found while writing this post:

 

 

When I click on that link or cut and paste it in Chrome or IE, this is what I get:

 

 

So far, there is no pattern to it that I can tell – and I have only begun to notice this in that past few weeks.

I am not sure what it is indicative of, but wondered if anyone else has encountered this and might have some insight.

Using Alumni Search to View Full Names of 3rd Degree Connections on LinkedIn

Last week, Patrick Ryan, a former colleague with whom I stay in touch, sent me an email with something he had discovered on LinkedIn. I asked him if he minded if I wrote about it and he said no, so here we go.

If you scroll down your LinkedIn home page, you’ll find the “Just joined LinkedIn” section with Colleagues and Alumni.

If you click on the school name under Alumni, you’ll be taken to an attractive dashboard with some interesting information.

 

 

From here, you can change the years attended, show alumni that don’t show a graduation date, and of course search.

When you configure your search and see some 3rd degree connections without full names, this is what they will look like – first name only:

 

 

If you click on “Connect” and you’re using either Chrome, Firefox or Safari (not IE – sorry), you’ll get a pop up that will allow you to send the person an invitation, and it will also show the person’s full name.

 

 

Okay – I am sure some of you are thinking, “Cool – but this is extremely limited because I can only search alumni from my school.”

Sure, it’s limited, but let’s just say you can similarly search through any school that’s in the education section of your LinkedIn profile.

Oh, and each school as a school ID. For example, mine is 18570.

 

 

Final Thoughts

You don’t need to have a premium LinkedIn account to view any public profile and see the full names of people who are not 1st or 2nd degree connections.

However, it’s not safe to assume that the ways in which we can currently search for and view the information on LinkedIn profiles beyond our network will remain unchanged.

In fact, I believe we can expect LinkedIn to develop ways that limit the ability to find and view certain info on LinkedIn profiles for free – and why shouldn’t we? LinkedIn isn’t a non-profit, and just as any other for-profit company, it’s their prerogative to look for ways to make money and to reasonably limit giving away too much for free.

Will LinkedIn read this post and change the ability to view full names of 3rd degree connections via alumni search?

Yes, they will read this post (Hi LinkedIn team – special shout-out to the Ninja!).

Maybe they will do something to change the appropriate functionality.

If they do, I’m happy to have helped.

Oh – and be sure to check out the comments.  Several readers offered other ways of revealing the full names of 3rd degree connections on LinkedIn.

Anything worth doing is worth measuring, and sourcing isn’t exempt from this.

If you want to know which method of sourcing has the highest ROI in terms of enabling a person to find more of the right people more quickly, then you’re in luck – because that’s what this post is about.

Human capital data comes in many forms – resumes, social network profiles, blogs, bios, press resleases, etc. – and I have found that a key and critical aspect of sources of human capital data that many people fail to formally recognize is the depth and completeness of the data that can yield information through review and analysis.

When it comes to leveraging information systems such as the Internet, applicant tracking systems, social networking sites, job board databases, etc. for sourcing and recruiting – the operative word is “information.”

Data is the lowest level of abstraction from which information can be derived. For data to become information, it must be interpreted and take on a meaning.

Generally, the quality and amount of information that can be gleaned from any particular source is directly linked and limited to the quality and amount of data present to be reviewed and analyzed. How useful is an information system supported by only a small amount of limited data?

In this post, I will:

• Review the major sources of human capital data
• Examine sourcing return on time invested
• Explore the potential candidate’s point of view
• Ask you to take a quick sourcing test

Ready?

ATS, Job Board Resume Databases

Resumes typically represent the deepest source of human capital data.

While the accuracy of them can be argued (albeit no differently than social media profiles) – most resumes contain significant and specifically professional information about the people who wrote them.

Even when poorly written, most resumes contain:

• A summary of experience
• Objectives that can give you insight into the types of opportunities they are interested in
• A work history that can give you an idea of their capabilities based on their past responsibilities and experience at specific companies, as well as an educated guess as to their desired compensation
• A full address, which can be critical in making an educated guess at whether or not they might be open to a particular commute

LinkedIn Profiles (CV’s?)

LinkedIn is the one stand-out social networking application that has a decent number of profiles with deep human capital data.

Although not a resume database, you can typically find (and thus search for and target) more employment qualification-related information than anywhere else outside of an actual resume database.

While LinkedIn calls them “profiles,” and some contain very little information other than 1 title and 1 employer, some LinkedIn users fill their profiles out just as they would their resume.

In fact, with the employment market in relatively bad shape, there are a number of articles advising job seekers to do exactly that – fill out their profile as they would a resume.

And now, LinkedIn even offers the ability to convert your LinkedIn profile into a resume(fantastic move, by the way!).

It also doesn’t hurt that LinkedIn has a robust search interface, supporting full Boolean logic as well as a number of LinkedIn-specific advanced search operators. Great search interface + deep human capital data = highly leveragable information system for talent identification.

Of course, it can’t be overlooked that there are more incomplete and shallow LinkedIn profiles than there are complete and fully fleshed out profiles, so all is not perfect in LinkedIn land.

Additionally, while LinkedIn has started to add some more specific location options for people to select (for example, my zip code gives me the option to select Alpharetta or Atlanta), many people still use their major metro area as the location on their profile (I do).

This can make it difficult to find people who are likely to be close to the location of the job you are sourcing for and thus “recruitable.”

What About Facebook, Twitter, and Google+?

While many people in the recruiting and staffing industry get REALLY excited about Facebook, Google+ and Twitter - I don’t.

Before you recoil in absolute horror that I haven’t jumped on the bandwagon with everyone else, let me say that I’m a big fan of leveraging  any/all social networking sites (provided your target talent uses them to a good degree, of course).

Yes, I they’re cool, and yes, I use them.

However, I refuse to get so blinded by their perceived potential and the hype in the sourcing/recruiting community that I fail to see their limitations.

You can certainly use Twitter, Google+ and Facebook to identify and contact potential candidates – there’s no arguing that. While Twitter is highly searchable, supporting Boolean queries and their own set of advanced search operators, Facebook isn’t (although it does offer you access to the largest single repository of people on the planet), and Google+ isn’t nearly as searchable as it should be given that it’s a Google creation.

However, regardless of “searchability,” none of those sites offers much professional data about the people who use them, or at least not the right types of information that can help a sourcer or recruiter gain any significant insight into specific skills, experience (including precise responsibilities and capability as well as overall years and career progression), and specific location.

You might get lucky to see a title on Facebook, Twitter, or Google+, and you might find people talking about their line of work, but the people who do mention titles and in some cases even employers is the vast minority.

Lastly – when it comes to social networking sites like Google+, Facebook, and Twitter, even when people do mention something work related online that can enable you to try to guess what it is they do, in many cases they do so using non-standard terminology, which poses an additional challenge to talent identification.

Shallow Human Capital Data

Facebook, Twitter and Google+ can be effectively leveraged for employer and recruiter branding, marketing, online community development, and socializing job opportunies (that’s social media speak for “job posting”) – which are largely passive methods of talent attraction.

However, as shallow sources of human capital data, Facebook, Twitter and Google+ are not particularly effective for active candidate identification.

When I say “active candidate identification,” I’m not referral to job seeking status (people actively seeking employment) – I’m referring to the process of actively searching for and identifying candidates with specific experience and qualifications that are highly likely to match specific hiring needs.

Posting jobs is a passive method of identifying potential candidates, because you post the job and then sit and wait for people to do the work of identifying themselves.

There is no doubt you can find and contact LOADS of people using Facebook, Twitter and Google+. However, in most cases, you have no real idea how much and exactly what kind of experience these people have prior to contacting them, and in many cases, you don’t know precisely where they live.

Just because they list that they have their CPA, or that they belong to a nursing association, or they are a “fan” of a PHP developer page - it certainly does not guarantee you of anything beyond that.

Non-Resume Internet Research

Using Internet search engines such as Google, Bing, Blekko, et al, to search for and sift through human capital data can definitely produce results.

I won’t argue that. However, once you go beyond resumes (the deepest sources of human capital data), you quickly enter the shallow end of the human capital data pool - press releases, blog posts and comments, articles, etc.

I would never suggest that these shallow data sources can’t be leveraged for sourcing and recruiting – but my point is that the intrinsic probability that any particular non-resume search result is qualified for your hiring needs is LOW.

This is because less data means less information available to be gleaned about the potential candidate – leaving us with little to no idea as to their professional experience and qualifications, and even specific location in many cases.

Expect a Return on your Time Invested

Maybe some sourcers and recruiters like to find and contact lots of people because they get paid to just be social and make lots of friends online.

Maybe some companies think it’s productive and cost effective to sift through and contact large quantities of people who aren’t qualified for, would not be interested in, and/or would not commute (or relo!) to the opportunity they are being sourced/identified for.

I certainly don’t! Who does anyway?

Wait – please don’t raise your hand (not you – that other person).

As shallow sources of information, Facebook, Twitter, Google+ and practically all sources of non-resume human capital data on the Internet simply don’t have much professional-experience/qualification-relevant information.

Less and incomplete data doesn’t really make for a heavily leverageable information system.

At least not when it comes to talent identification where it’s more than helpful to know a little bit about someone’s experience before you contact them.

Value to the Candidate?

Candidates generally appreciate being contacted for opportunities that are in their “ballpark” when it comes to location and responsibilities.

Most candidates don’t appreciate being contacted for opportunities that aren’t.

Think about this for a second – what VALUE are you providing to people that you find and contact using shallow sources of human capital data when they are in fact not even remotely qualified or interested in your opportunity?

Most people don’t appreciate being contacted by recruiters only to end up being used as a tool in your networking/referral recruiting efforts because you didn’t have enough information about them to possibly provide anything of value to them.

Yes, I remember the days of just picking up the phone and calling people with little to no information – but take a second to answer this question: Is this kind of practice and process the best and highest ROI method of sourcing and recruiting?I think not.

Critical Candidate Matching Variables

Deeper and more detailed human capital data enables more precise and controlled searches, allowing sourcers and recruiters to be able to make an educated decision to contact people based on capability and experience rather than blind faith or a guess based on perhaps a title alone.

With resumes or fully fleshed out LinkedIn profiles, a talented sourcer or recruiter can effectively control critical candidate variables such as location, potential opportunity match, and experience/capability – including years of experience, which can tie into compensation.

Sourcing Test: Which Person is More Likely to be Interested and Qualified?

Here is a dramatic and certainly more practical example of deep vs. shallow human capital data: If you were responsible for filling a position for a Business Analyst with energy industry experience and specific experience working on SAP projects and using UML, which of the following people has the higher probability of being both qualified and interested in your opportunity?

Person #1: LinkedIn Profile

 

Person #2: Twitter Bio

 

 

The contrast is dramatic.

The LinkedIn profile is essentially filled out as completely as a resume would be, and as such, we can feel confident when contacting this person because their experience appears to closely align with our opportunity, and even if they aren’t recruitable, they’ll have to admit the opportunity was relevant.

The Twitter profile mentions the title of “Business Analyst,” but little else – we have no idea as to this person’s industry or project experience. While we can cross reference the Twitter Bio with LinkedIn, when doing so, we can see by looking at her profile that she does not appear to have any energy industry experience, and we cannot tell if she has any SAP project or UML experience.

If you had a choice between using either an information system that had shallow data on the people contained within, or an information system that had deep data on the people contained within - and you could only choose one – which would you choose and why?

I know which one I would choose – all things being equal, I would choose the information system with the deep and more complete human capital data.

That way, I can run creative and effective queries to search for, find, and contact people based on specific experience and qualifications. Why would anyone choose any different?

Final Thoughts

You can find and hire people by searching any source of human capital data – resume or otherwise.

However, searching Facebook, Twitter, Google+, blogs, the Internet and other similarly shallow sources of human capital data requires a higher amount of effort for a smaller return – what I call low yield sourcing and recruiting.

While there is undoubtedly more shallow human capital data than deep human capital data, does it sound like a good idea to go out of your way to focus on low yield sourcing and recruiting?

When it comes to proactive candidate sourcing (e.g., searching for people and not posting jobs and waiting for responses), I’d argue that the deep sources of human capital data such as resume databases, applicant tracking systems, LinkedIn, and Internet resumes are responsible for producing 80% of the search based sourcing and recruiting results (hires).

Conversely, the shallow sources of human capital data such as Facebook, Twitter, Google+ and and non-resume Internet research produce 20% of the active-search based sourcing and recruiting results. You essentially have two paths:

1. Find and contact more uninterested and unqualified people
2. Find and contact more interested and qualified people

Which one will you take?

Does your employer give you a choice?

If you have nearly any tenure in HR, sourcing or recruiting, you’ve probably heard something about “semantic search” and perhaps you would like to learn more.

Well – you’ve found the right article.

As a follow-up to my recent Slideshare on AI sourcing and matching, I am going to provide an overview of semantic search, the claims that semantic search vendors often make, explain how semantic search applications actually work, and expose some practical limitations of semantic search  recruiting solutions.

Additionally, I will classify the 5 basic levels of semantic search and give you examples of how you can conduct Level 3 Semantic Search (Grammatical/Natural) with Monster, Bing, and any search engine that allows for fixed or configurable proximity.

But first – let’s define “semantic search.”

What is Semantic Search?

Semantics is the study of meaning, inherent at the levels of words, phrases, and sentences.

Semantic search is most often used to describe searching beyond the literal lexical (exact word for word) match and into the meaning of words and phrases at the conceptual and contextual level, and sentences at the grammatical level.

When sourcing candidates, semantic search can be achieved at the conceptual level when a search for a specific term (e.g., Java) also yields matches on related terms (e.g., J2EE, EJB, servlets, etc). – words that are related conceptually.

As another example, in the healthcare space, a semantic search for “cancer” could also produce positive hits on terms such as oncology, lymphoma, tumor, etc.

Words and phrases by themselves can be somewhat ambiguous, but are less so when taken in context - using surrounding words or passages that can shed light on the intended meaning.

For example, “Java” is a software programming language, but it is also used to refer to coffee, and it is also an Indonesian island. A quick Twitter search for “Java” will typically net you a mix of references to Java. By reading each tweet and the text surrounding “Java,” we can easily disambiguate the reference to “Java” and divine the intended meaning.

Below you can see Java referenced on Twitter in 3 very different ways in 3 successive tweets, and the context tells you how to interpret the meaning of “Java” in each one:

Why Should HR/Recruiting Professionals Care about Semantic Search?

There is more information available about more people today than ever, and the volume is only going to increase and the rate at which is accumulates is accelerating.

Sifting through an ever-increasingly large amount of human capital data in the form of resumes, social media profiles (LinkedIn, Twitter, Facebook, etc.), blogs and other sources is a significant challenge.

The promise and potential of semantic search is that it can help you more quickly and easily cut through massive volumes of potential candidate information to help you find more of the right people faster than standard methods.

Choose Your Own Adventure!

Now that you understand semantics and the basic concepts of semantic search, you have a choice:

1. If you don’t particularly care to get into the details of how solutions that claim to use semantic search actually work and achieve their claims, you can skip all the way to the end for a presentation on the 5 Levels of semantic search. In that presentation that you can find a couple of examples of how to achieve Level 3 semantic search with Monster or any search engine that offers proximity search, which allows you to control how close your search terms are to each other.
2. If you currently use a matching application that claims to leverage semantic search (e.g., Monster’s 6Sense), if you’re considering purchasing/implementing such a solution, or if you’re just curious how these kinds of applications achieve their claims, don’t skip ahead and continue reading.

Semantic Search Claims for Sourcing and Recruiting

Many vendors are quick to explain that their semantic search solution can help you and/or (wink) your team to “stop wasting time trying to create difficult and complex Boolean search strings”, and instead, let “intelligent search and match” applications do the work for you.

Some claim that “a single query will give you the results you need – no more re-querying, no more waste of time!”

Going further, semantic search solutions for the recruiting industry commonly state that their offerings:

• Understand titles, skills, and concepts
• Automatically analyze and define relationships between words and concepts
• Intuit and infer experience by context
• Perform pattern recognition
• Perform fuzzy matching

Sounds Great – But How Do They Really Work?

Over the years, I’ve had many people attempt to sell me on the benefits of semantic search when it comes to sourcing potential candidates, and I have also had the opportunity to use and evaluate quite a few semantic search solutions, including pretty much all of the usual suspects in the space.

My experience and skill with regard to human capital data information retrieval information retrieval affords me some unique insight as to how the technologies and techniques semantic search vendors utilize to make their claims actually work, as well as their limitations specific to human capital data. More on that last bit later.

First, let’s get into how semantic search applications for recruiting actually work.

When semantic search vendors make claims that their applications can automatically understand titles, skills, and concepts, analyze and define relationships between words and concepts, intuit and infer experience by context, perform pattern recognition and fuzzy matching, they are typically using 1 or more of the following to do so:

Resume Parsing

Parsing slices and dices resumes and extracts useful information contextually based on the structure of most resumes.

A good parser can take a resume and break it down to its component parts and “understand” a person’s experience.

Resume parsing can be used to extract skill words and differentiate between terms mentioned in skills summaries vs. those that are mentioned in the body of the resume – the latter having a higher probability of being indicative of real experience. Resume parsers can also typically extract titles and employers and some can even reliably identify the most recent title and employer.

Solid parsing technology can correctly identify addresses and education information and “realize” that “George Washington” in an address is likely a street name, but in an education section a University.

Some parsers can even determine current vs. dated experience with specific skills, as well as automatically calculate years of experience with specific skills, management, and overall years of work experience based on date analysis. Being able to control years of experience can help find people who aren’t under- or overqualified or not likely to be in the compensation range of the opening you are sourcing/recruiting for.

Resume parsing can result in highly structured data, which can enable a recruiter to move beyond free text search and to search for information contextually in specific sections/fields, such as current title, current experience, education, etc.

A more automated way of achieving semantic search via parsed resume data is to take basic search terms entered by a sourcer or recruiter and weight search results based on recency of related titles and experience, based on data parsed and identified as more recent, as well as calculated years of experience (e.g., Java and related terms mentioned in most recent work experience, dated ’9/06 to Present’).

So now you know that when you hear that a semantic search application can “automatically understand titles and skills” and can “intuit and infer experience by context,” not only do you know what they’re talking about, you know at least one of the ways they try to make good on that claim.

Taxonomies and Ontologies

Some semantic search solutions for recruiting leverage ontologies and taxonomies.

Taxonomy is the science which deals with the study of identifying, grouping, and naming things according to their established natural relationship. An ontology is a “formal representation of knowledge as a set of concepts within a domain, and the relationships between those concepts.”

As complex as those definitions may sound, they are really quite easy to understand when it comes to how vendors utilize taxonomies and ontologies to achieve semantic search.

Taxonomies and ontologies are leveraged by semantic search solutions for recruiting and staffing as a back-end list of keywords organized by concept and relationship so that when you search for a term or phrase, the solution can compare your search against terms and phrases it “knows” are conceptually related.

A common taxonomy used in recruiting solutions is a parent-child, hierarchical (directional, one way) taxonomy. Wikipedia uses this simple way of explaining the parent-child relationship: A car is a subtype of vehicle, so any car is also a vehicle, but not every vehicle is a car.

Hierarchical Taxonomy

With a hierarchical taxonomy for accounting terminology, if you searched for “SOX 404,” you should get positive hits and relevance ranking from the term “SOX 404″ as well as “accounting,” because the system can recognize that “SOX 404″ is an accounting-related “child” term/concept tied to the “parent” term “accounting.”

In a true hierarchical taxonomy, if you searched for “accounting,” you should only get positive hits and ranking on the term “accounting” and not on mentions of “SOX 404,” because not all accounting-related work involves SOX 404.

In other words, SOX 404 is accounting-related work, but not all accounting work is SOX 404-related.

Conceptual Search

A semantic search solution using a hierarchical taxonomy can help you find terms and phrases other than the ones you specifically searched for, because they compare your search terms with the taxonomy and return results that not only mention your keywords, but also related terminology.

This is a form of “conceptual search” – you search for 1 term, and you can get results mentioning all related concepts as well as your original search term.

In addition to hierarchical relationships, semantic search solutions may also perform conceptual searching based on synonymous terms and phrases.

For example, if you searched for “Director of Tax,” a well developed taxonomy would also return results for all of the title variants you didn’t actually search for, but are the same, such as “Tax Director,” “Director, Tax,” etc. This form of conceptual search can be useful for finding common abbreviations for phrases, such as CPA and “C.P.A” from a search for “Certified Public Accountant,” and vice versa.

A comprehensive taxonomy can be especially helpful for Information Technology sourcers and recruiters, as it can be difficult to know or even remember all of the various ways certain technologies can be referenced (SQL 2008, SQL Server, MSSQL, etc.).

Statistical Methods

Rather than relying on pre-built taxonomies to define relationships between titles, terms and concepts, some semantic search solutions use complex statistical methods in an attempt to automatically “understand” language and relationships between words.

While I am not aware of any semantic search vendor supplying solutions to the recruiting industry that publicly explains their statistical methods, thankfully Google gives us a tiny bit of insight of how such an approach works.

Google has found that keywords with the same or similar meanings in a natural language sense tend to be “close” in units of Google distance, while words with dissimilar meanings tend to be farther apart.

Here is the equation for the Google distance, which is a measure of semantic interrelatedness derived from the number of hits returned by the Google search engine for a given set of keywords.

That was easy, right?

Semantic Clustering, Machine Learning, Pattern Recognition – Oh My!

I don’t pretend to understand semantic clustering and machine learning at the technical level, but I do have a good understanding of what they are used for and how they work at a high level, specifically with regard to sourcing and matching candidates from human capital data.

Semantic clustering is a non-interactive and unsupervised machine learning technique seeking to automatically analyze and define relationships between words and concepts.

For candidate sourcing purposes, algorithms are created to automatically learn to recognize complex patterns, “learn” and draw relationships from human capital data (resumes, social network profiles, etc.).

Rather the relying on a static taxonomy, semantic clustering allows for dynamic concept matching.

Based on statistical analysis/algorithms and pattern recognition, an application can “learn” that C# is related to .Net, due in part to keyword frequency and proximity that it has analyzed across thousands to millions of documents.

A query cloud offers an excellent visualization of semantic clustering – you can see and choose from a group of terms and phrases that the semantic search solution has determined to be related to your search term.

Here is an example of a query cloud for C#:

While semantic clustering can quickly and easily find related terms, the question has to be asked of whether or not the related terms are actually relevant. Only the person conducting the search can make that determination.

Fuzzy Logic

When an application claims to perform fuzzy matching, it is apply fuzzy logic to the search, which finds approximate matches to a pattern in a string.

Fuzzy logic is especially useful to automatically search for slight phrase variations and word misspellings. Most sourcers/recruiters do not take the time to search for misspellings, and understandably so as it is quite laborious. However, a good fuzzy matching solution will find your exact search terms as well as any slight spelling variation, intentional or unintentional.

If you don’t search for misspellings, you’re missing people:

The 5 Levels of Semantic Search

Now that you have a basic understanding of the concept of semantic search and how applications using semantic search actually work, I’d like to introduce you to what I believe are the 5 basic levels of semantic search.

Intended for HR professionals, sourcers and recruiters, this presentation explains and explores the concepts of semantics and semantic search, including the 5 Levels of Semantic Search: Conceptual Search, Contextual Search, Grammatical/Natural Language Search, Inferential Search, and Tagging.

You’ll also see some examples of how you can achieve Level 3 semantic search using Monster (classic search) or any search engine that allows for fixed or configurable proximity search.

Semantic Search for Sourcing and Recruiting

View more presentations from Glen Cathey Semantic Search for Recruiting: The Good

I love technology and anything that can make me better and faster at what I do. Semantic search solutions for sourcing candidates can provide many benefits, including:

• Reducing the time to find relevant matches
• Lessening or eliminating the need for recruiters to have deep and specialized knowledge within an industry or skill set
• Reducing and even eliminating time spent on initial research
• The ability to go beyond literal, identical lexical matching
• Leveling the playing field for those with less sourcing experience or ability
• Making an inexperienced person look like a sourcing wizard
• Boosting teams with low search/sourcing capability
• Working well for positions where titles effectively identify matches and where there is a low volume and variety of keywords
• Working well for organizations with a high volume of unchanging hiring needs

Semantic Search for Recruiting: The Bad

On the other hand, you should be aware of some issues associated with blindly trusting semantic search solutions, including:

• Just because terms are related, it doesn’t automatically make them relevant to the search
• Removing thought from the talent identification  process
• The danger of eliminating the need for recruiters to understand what they’re actually searching for
• Difficulty with information technology, healthcare, and other sectors/verticals with ever-changing technology and terminology
• Finding some people, but eliminating and/or burying others
• Finding the best matches based on keywords present, as opposed to the best people
• The inability to search for what isn’t explicitly stated - applications will only return results that mention required keywords and their variants
• The fact that many people have skills and experience that are simply not mentioned anywhere in their resumes and thus they cannot be retrieved via any direct search method
• They level the playing field – if competing companies use the same software solution, they will both find (and miss!) the exact same people
• The fact that a single search cannot find all of the best people – every search both includes and excludes qualified candidates
• They can favor keyword rich resumes/profiles, yet keyword poor resumes/profiles may in fact represent better candidates that keyword rich resumes

Semantic Search for Sourcing & Recruiting: The Bottom Line

The potential of semantic search for talent identification and acquisition is powerful and exciting!

However, it’s important to realize that with technology that’s been on the market for over a decade, sourcers and recruiters have already been able to “manually” achieve Levels 1-4 semantic search for a while now, and there are some solutions available today that allow for searchable tagging as well (Level 5).

On the other hand, using software for automating semantic search/match can allow you to quickly, easily and somewhat reliably achieve Levels 1-2 semantic search, depending on the vendor/solution you choose. At this time, true Level 3-5 semantic search is beyond the reach of today’s semantic search/match applications (IMHO).

One of the main and inescapable problems with any automated semantic search/match solution is that human capital data is quite often incomplete and unstructured. Let’s face it – no company is looking to find people because they mention specific keywords and titles – everyone’s looking for their next great hire who has specific skills and experience which may not even be explicitly mentioned in a resume, on a LinkedIn profile, in a Twitter bio, etc.

Matching software can work with what’s there (text that’s present), but they can’t match on what’s not there (text that isn’t present). On the other hand, one thing that humans do incredibly well is instantly perform dynamic inference, more commonly known as “reading between the lines.” Perhaps at some point in the future, software will be able to somewhat reliably infer experience and capability beyond text that is present, but it can’t be done today beyond guessing (e.g., “Were you looking for _____________?”).

Food for thought – how would you like to explain to a candidate that the reason why they weren’t considered for a job was because your semantic search application didn’t think they were a match based on their resume? How would you feel if you were turned down in consideration for a job because a software solution didn’t “like” your resume? Do we really want to rely 100% on a software solution that seems to make our life easier when it can result in missing and altogether eliminating some of the best people available?

While software can retrieve and move data, data requires analysis to yield information and produce knowledge which can facilitate decision making. That’s why these solutions are referred to as Decision Support Systems - the operative word being “support,” because they don’t (and should not!) make the decisions for you – these solutions provide you with data to interpret for information to make an informed decision.

In the case of sourcing/recruiting – it’s deciding who to engage, screen, and potentially recruit.