Category Archives: Semantic Search

The Best Boolean and Semantic Search Tool

While many people are hungry for specific Boolean search strings to copy and paste and for search tools that make searching for people “easier” and even “do the thinking for you,” there simply is nothing that can come remotely close to what you can do when you think properly and ask the right questions.

Yoda Think Before You Search

That’s right – the most powerful thing you can incorporate into your people search efforts isn’t Boolean logic, a search “hack,” Chrome extension, search aggregator, semantic search solution or anything you can buy – it’s your brain. Your level of understanding of and appreciation for the unique challenges posed by human capital data in any form (social media profiles, resumes, etc.) directly correlates to your ability to extract value from any data source. The same is true of the thought processes you apply before and during your search efforts.

A little over a year ago, I presented for the 3rd time at LinkedIn’s Talent Connect event in London, and I spoke about how to leverage LinkedIn’s massive stockpile of human capital data for sourcing and recruiting. LinkedIn recorded the session and uploaded the video to YouTube, and I recently noticed the video had over 65,000 views. Now, while that is puny in comparison to the nearly 1B views Adele’s Hello video has racked up, I was surprised to see so many views given the niche content.

Although the source of human capital data that I focus on in the video happens to be LinkedIn, practically everything I talk about is equally applicable to any source you can use to find people to recruit.

So, if you use any source of human capital data to find and recruit people (e.g., your ATS/CRM, resume databases, LinkedIn, Google, Facebook, Github, etc.) and you really want to understand how to best approach your talent sourcing efforts, I recommend watching this video when you have the time.

Enjoy, and feel free to let me know your thoughts!

 

LinkedIn’s New Non-Boolean Search Functionality

I originally published this post on LinkedIn, but am reposting here to ensure my blog readers catch it.

When I attended LinkedIn’s Talent Connect 2015 conference in Anaheim, CA and I was able to take some video of Eddie Vivas, Head of Talent Solutions Product for LinkedIn, formerly the Founder and Chief Product Officer at Bright.com (acquired by LinkedIn), talking about and briefly demonstrating LinkedIn Recruiter’s new search interface and functionality.

Check it out – be sure to switch to 1080p and go full screen.

As Eddie says at 1:35 into the video, “You guys ready to see some cool shit?”

I’ve attended and spoken at every Talent Connect event, and I’ve been waiting 5 long years for LinkedIn to make some major changes to their search interface and functionality.

Whatever you think of LinkedIn, they have a ton of professional human capital data, and the value of data is directly proportional to the ability of users to quickly, easily and precisely retrieve actionable data.

Definition of Actionable

The more easily recruiters can quickly and precisely retrieve profiles of people who have a decent probability of being the right match and also likely to respond to outreach efforts, the more actionable (and thus valuable) LinkedIn’s data becomes.

Although the video and a few other assets I share below don’t show you everything that’s coming to the new Recruiter search experience, I’m going to run through a few things that will definitely make LinkedIn’s data more actionable than ever before for recruiters, and none of them involve Boolean search.

Dynamic Semantic Search Suggestions

LinkedIn claims Recruiter’s new search “learns as you go,” dynamically adjusting suggested synonymous and related search terms as you enter new terms.

Think of this as LinkedIn Skills on steroids and integrated seamlessly and practically into the search experience.

As you add search terms, Recruiter will provide you with a list of the top titles, skills, companies and schools associated with your target candidates and you can choose to incorporate the suggestions  into your search (or not).

Next-Generation-of-LinkedIn-Recruiter

I’m presuming that as you add search terms they effectively create Boolean “OR” statements whereby results will match at least one of the terms.

Historically, I’ve referred to this as conceptual search or Level 2 Talent Mining. While very effective, the challenge for most people is that they don’t know all of the various ways in which people with specific skills and experience might make mention of them, leading recruiters to craft searches that actually create Dark Matter.

Based on what I can see, this new Recruiter functionality should go a long way in reducing LinkedIn’s Dark Matter, helping people build more inclusive searches by automatically suggesting additional potentially relevant search terms to return results of people who would likely not ever be found via traditional keyword search, given the wide variety of ways people can express the same skills and experience.

LinkedIn Profile Matching

You will also be able to find potential candidates using an employee’s (and perhaps anyone’s?) profile.

Essentially using a profile to automatically build a search – Recruiter’s new functionality will:

Automatically build your search string using the job title, skills, company, and industry, listed on the employee’s profile. It will show you the terms it used to build the search string, let you add or remove terms, and instantly update the list of members who meet your search criteria – helping you quickly identify the members who are a match for your open job.

I can’t wait to get my hands on this to see how well it actually performs.

Search Spotlights

This is what I am most excited about – Recruiter’s new search will offer users the ability to quickly and easily filter results by potential candidates who (LinkedIn claims) are 2-3X more likely to engage, based on relationships and interactions on LinkedIn, including:

  • Company connections
  • Past applicants
  • People engaged with your company on LinkedIn
  • People in your competitors’ talent pool (“Who your competitors target”)
  • Who’s potentially ready for a move – people who have been in their current role for 1-5 years
  • Interested candidates – people who have indicated to LinkedIn that they are open to new opportunities

New LinkedIn Recruiter Search Spotlights

I find these last 2 to be especially interesting and particularly useful- I’ve been wondering how and when LinkedIn would allow people to show recruiters they are open to new opportunities.

Granted, 1-5 years is a HUGE window and may not be as predictive or precise as some would like, but it’s a start. Also, I am not sure why LinkedIn wouldn’t offer a spotlight showing you only people who are within 30-60 days of their work anniversary – company and/or title – as this is a time when many people think about their future and could be more open to making a change.

Eddie claims they are launching with 7 different spotlights, hinting that perhaps more spotlights are likely coming in the future.

But What About Boolean?

Don’t worry – LinkedIn claims that “Advanced recruiters can continue to use their own Boolean search strings.”

However, as I’ve always stated, effective search isn’t about Boolean logic – it’s about information retrieval, and I am excited to see LinkedIn provide users with additional, and what appear to be practically useful and effective, means of retrieving a higher quantity (through more inclusive search) of relevant results – people who have a higher probability of being the right match and more likely to respond to recruiters.

When is it Coming and What Do You Think?

Apparently LinkedIn has and/or will beta launch the new Recruiter search functionality to select customers in Q4 2015, and a general launch is planned for Q1 2016.

From a few folks who have been lucky enough to play around with the new search functionality this year, I’ve heard it’s not “fully baked” yet, but I don’t find that surprising.

What do you think about these new Recruiter search enhancements?

Important Facebook Graph Search Developments

 

It is difficult to ignore the potential of Facebook when it comes to sourcing and recruiting given that it has 1.38B monthly active users and 890M daily active users.

When Graph Search was introduced back in 2013, it was an amazingly powerful people sourcing tool.  However, recent changes have somewhat reduced its efficacy. While some people might think that Facebook’s Graph Search is effectively dead, it is still very much alive. In fact, Graph Search is now live on mobile (more on that in a bit).

Although it’s not what it used to be, Graph Search still allows you to write some very effective natural language queries to retrieve Facebook profiles, as you can search by title, company, location, languages, etc., and Graph Search is still a ridiculously powerful gender diversity sourcing tool (where legal, of course).

Here’s a search for female software engineers who work for Google, live near New York and speak French.

Facebook Graph Search 2015 Diversity Google Software Engineers Near New York who speak French

That’s some good stuff right there!

While people searches like that will satisfy the average user, hardcore sourcers might lament the loss of the ability to create the more advanced and inclusive queries they used to in the past, and the extensive search refinements associated with Graph Search on the right rail are now gone, with trending posts now taking up that screen real estate.

Once you try to go much beyond searches like the one above, Facebook will humbly apologize for not being able to find any results for your search. Continue reading

Boolean Strings, Semantic and Natural Language Search – Oh My!

An entertaining blog post by Matt Charney was recently brought to my attention in which he tells the world to shut up and stop talking about Boolean strings – he argues that Boolean search is a dying art and that “investing time or energy into becoming a master at Boolean is a lot like learning the fine art of calligraphy or opening a Delorean dealership.”

You can read the snippet regarding Boolean Strings below – click the image to be taken to the entire post, in which Matt addresses mobile recruiting and employer branding.

Matt Charney Boolean Strings

I enjoyed Matt’s post and his approach, but I did not find his arguments to be thoroughly sound – although I suspect he wasn’t trying to make them so (after all, his blog is titled “Snark Attack”).

I’m going to take the opportunity to address the points Matt raised – not because I am trying to stay “relevant,” as some might suggest (my blog is a not-for-profit personal passion and I don’t consult/train for a fee), and also not because I have a vested interest in “keeping Boolean search alive” (because I really don’t) – rather, because I am still amazed that a fundamental lack of understanding of search and information retrieval – both “manual” Boolean search and “automated” taxonomy driven and/or AI-powered semantic search – and I am constantly trying to help people not only understand both, but also appreciate their intrinsic limitations, as well as separate reality from hype.

So, without further ado: Continue reading

Is Boolean Search Boring and Less Effective than Semantic Search?

 

Boolean Search is Boring

Do you think Boolean search is boring, tiresome and ineffective, and that semantic search delivers faster results that count?

I was struck by the image Marc Drees used in his #SOSUEU: the day after post, which you can see above.

I would have loved to sit on that panel discussion and contribute my experience and thoughts on the subject – I was actually supposed to attend and speak but I left the sponsoring company just prior to the event.

Such is life. :)

Regardless, I am happy to weigh in here, and I believe that the majority of people simply aren’t looking at search properly in the first place.

I’ll address the statements from #SOSUEU in order.

Boolean Search is Boring

Let’s hit the reset button first and get a couple of things straight:

If Boolean search is boring, then searching the Internet, Amazon, etc.,  for anything is boring. Any time you use more than 1 term in your search on Google, Bing, Amazon, eBay, etc., you’re using Boolean search. The same is true with LinkedIn and many other sites you can search to find people. Am I alone in this simple understanding?

This may confuse some people, but “Boolean Search” isn’t about Boolean – it’s about search. Searching is about finding things you need and want, and there are many ways that you can search for and find those things. Do you find it more “exciting” to select from a list or check a box on a LinkedIn facet?

Github list and LinkedIn Facet

Whether you type in keywords, select from a list, check a box, apply a filter, etc., all you’re doing is configuring a query to get results to review.

I don’t think there is anything intrinsically “boring” about Boolean operators. I think the real issue is that some recruiters just don’t enjoy searching for people, and if you don’t enjoy something it’s common to find it boring. The same people who bash Boolean search don’t find typing terms into separate search fields, picking from lists and checking boxes exciting or particularly enjoyable.

Some people really like searching databases, social networks, the Internet, etc., for people to engage and recruit. Others would be happy to post jobs and wait for people to come to them and would rather not ever have to search for potential candidates to engage.

To say that Boolean search is boring is to say that carefully looking for and trying to find people (paraphrasing Merriam-Webster’s definition of search) is boring. Semantic search solutions alleviate the boredom of searching for those who find it tedious, because similar to posting a job and getting responses, semantic search solutions often allow you to enter minimal information and get results.

I’d be willing to bet that those same recruiters who don’t enjoy searching to find people to engage also don’t enjoy reviewing responses to job postings as many are unqualified – they would much rather be given a list of well matched people, which semantic search solutions claim to be able to do.

What do you think?

Boolean Search is Tiresome

If you think Boolean search is tiresome, I say you’re lazy.

Why?

Well, for basic Boolean search, we’re talking 2 operators and 2 of modifiers – in many search engines you don’t even need to type AND, as any old space will do.

Is typing in OR, -, ” ” and ( ) really tiresome?

Is filling out multiple search fields (e.g. Twitter below) any less tiresome than typing a couple of Boolean operators? By the way, the common elements of most “advanced search” interfaces are essentially AND’s (All of these words), OR’s (Any of these words), NOT’s (None of these words), and quotation marks (This exact phrase).  Oh wait – that’s basic Boolean, right? Snap!

Twitter Advanced Search Interface

While I love the concept of natural language queries, I actually find writing them tiresome and limiting (e.g. Facebook Graph Search).

Facebook Graph Search Tiresome

Is it less tiresome to use Facebook’s search fields? They’re all essentially linked by AND’s, btw.

Facebook Graph Search Interface

If there is anything that people really find tiresome about any non-semantic search, Boolean or otherwise, is that it requires you to think and expend mental energy.

I know – thinking is tough!

If you’re read a lot of my content over the years, you know I like to bring up the study of information retrieval techniques that bring human intelligence into the search process, otherwise known as Human–computer information retrieval (HCIR).

The term human–computer information retrieval was coined by Gary Marchionini who explained that “HCIR aims to empower people to explore large-scale information bases but demands that people also take responsibility for this control by expending cognitive and physical energy.”

I know the dream is to have computers read our minds so we don’t have to type a single search term – but until that day comes, you should be aware that experts in the field of HCIR do not believe that people should mentally “check out” of the information retrieval process and let semantic search/NLP algorithms/AI be solely responsible for the results.

Having said that, I can see why some people would see the process of building a massive OR string for all of the ways in which a person could possibly reference a certain skill or experience to ensure maximum inclusion as tiresome. It’s exhaustive work – especially if you don’t want to exclude great people who simply don’t reference their experience with the most commonly used search terms.

This is one of the main value propositions of semantic search solutions for people sourcing – through taxonomies and/or NLP-powered AI/algorithms, a user can enter in a single search term and effectively search for other related terms without requiring the user to know and search for all of the other related terms.

Sound great, right? Letting a taxonomies and/or algorithms doing the conceptual search work for you is certainly a lot less tiresome than having to perform research and pay attention to search results, looking for patterns of related and relevant terms to continually refine and improve Boolean searches.

To be sure, there are some solid semantic search offerings for talent sourcing on the market today that make sourcing talent faster and easier for people who find Boolean search boring, tiring, difficult and ineffective. However, to think that semantic search solutions don’t come with their own host of challenges and limitations would be ridiculous.

In case you haven’t see it before, you may want to quickly drive through my Slideshare on Artificial Intelligence and Black Box Semantic Search vs. Human Cognition and Sourcing derived from my 2010 SourceCon keynote to get a high-level overview of some of the challenges faced by semantic search solutions specific to talent sourcing.

If you don’t want to flip through the presentation, here’s a very brief summary:
  • Human capital data/text is often incomplete and widely varied – many people with the same job have different titles, explain their experience using different terms, and in many cases simply do not explicitly mention critical skills and experience
  • Semantic search solutions can only search for what is explicitly stated in resumes and social profiles
  • Taxonomies are difficult, if not impossible to make “complete” and thus they can exclude qualified talent
  • AI/NLP can be useful in determining related terms, but not necessarily relevant terms
  • Many semantic search solutions suffer from “once and done” query execution – there is no way to refine and improve searches or to exclude false positives/irrelevant results

Boolean Search is Ineffective

The effectiveness of Boolean search strings has more to do with the person writing the queries and the sources being searched and less to nothing to do with Boolean logic.

When used in a search, Boolean operators are essentially being used as a very basic query language, and according to Wikipedia, “an information retrieval query language attempts to find…information that is relevant to an area of inquiry.”

Any search a user conducts, whether they know it or not, is essentially a formal statement of an information need.

How effectively a user can translate their information need into a query/search string largely determines the relevance of the results – Boolean logic itself often has little to nothing to do with search relevance!

Assuming a sourcer/recruiter has a solid understanding of  what they’re looking for (a dangerous assumption, by the way – try giving 5 people the same job description and then ask them separately what they’re looking for), the effectiveness of any search they use, whether Boolean, faceted, semantic, etc., is more dependent upon the user’s ability to “explain” their needs to the system/site being searched via an effective query.

For example, let’s say you’re sourcing for a sales leader and you have a military veteran hiring initiative. Regardless of whether you decided to search your ATS (e.g. Taleo), LinkedIn, CareerBuilder, Indeed, etc., you’re essentially asking the same question, “Do you have anyone with experience leading sales teams who is also a veteran?” (among other things – just trying to keep it simple here).

How would you construct a Boolean search for a sales leader who is also a veteran?

How would (and/or could!) a semantic search engine search for a sales leader who is also a veteran?

Ultimately, it comes down to how many ways can someone who has sales leader experience could possibly express that experience on their resume or profile, and how many ways someone who is a veteran could possibly reference their veteran status.

Do you know them all?

Does any semantic search engine know them all? Some don’t know any because they simply aren’t included in their taxonomies. Others could use NLP to find some, but definitely not all. However, a person with decent sourcing skills could produce a veteran query like this one in about 5 minutes (not too tiresome) and continuously improve it:

(Army OR USAR OR “U.S.A.R.” OR “Army Reserve” OR “Army Reserves” OR Navy OR USN OR USNR OR “U.S.N.” OR “U.S.N.R.” OR “Naval Reserves” OR “Naval Reserve” OR “Air Force” OR USAF OR “U.S.A.F.” OR USFAR OR “U.S.A.F.R.” OR “Force Reserve” OR “Force Reserves” OR “Forces Reserve” OR “Forces Reserves” OR Marines OR “Marine Corp” OR “Marine Corps” OR USMC OR “U.S.M.C.” OR USMCR OR “U.S.M.C.R.” OR MARFORRES OR “Marine Expeditionary Force” OR MEF OR “Coast Guard” OR USCG OR “U.S.C.G.” OR USCGR OR “National Guard” OR Veteran OR “honorable discharge” OR “honorably discharged”)

The effectiveness of any search, Boolean or semantic, can be measured by the relevance of the results (e.g., a high percentage of the results are exactly what the searcher is looking for) and the inclusiveness of the results (how many relevant results are retrieved as a percentage of the relevant results available to be retrieved – those available but not retrieved are excluded into the abyss of Dark Matter).

Only the person conducting the search can judge the relevance of the results returned by any search, Boolean or semantic, as relevance is defined as the ability (as of an information retrieval system) to retrieve material that satisfies the needs of the user, and only the user truly knows what their needs are.

When it comes to inclusion, I am aware of some folks who are proponents of “good enough” searches and search solutions (e.g., finding some good people quickly is good enough and there is no need to find all of the best people).

Try telling your company’s executives that you really don’t care about finding the best people available to be found and that you believe that the quickest and easiest to find should be good enough for your company’s hiring needs.

Let me know how that works for you.

Okay, but what about Context and Weighting?

Some folks argue that Boolean search is ineffective due to the fact that Boolean searches are not contextual (e.g. you search for a term and it shows up not in the person’s recent experience, or in their experience at all) and that all terms in a query are given equal weight (e.g., if you search for 10 terms, some terms are likely to be more important than others, but basic Boolean logic doesn’t allow you to differentiate the value/relevance of specific terms).

Admittedly, some Boolean searches are.

However, if you have well parsed/structured data and a search interface that allows you to exploit that structured data, you can use simple Boolean logic to search contextually. For example, most recent/past employer and title, most recent/past experience, etc.

Some search engines do in fact allow you to assign different weights to terms within a single Boolean query (e.g. Lucene, dtSearch, etc.) – this functionality is sometimes referred to extended Boolean search. These same search engines allow you to search for terms in or exclude them from specific areas (e.g. top of the resume, bottom of the resume) via proximity search – functionality that also allows you to perform powerful user-specified semantic search at the verb/noun level to target people with specific responsibilities (have goosebumps yet?).

Okay, that was easy to address.

So, Is Boolean Search Boring and Less Effective than Semantic Search?

For some people, yes – Boolean search is boring, tiresome and less effective than semantic search.

For others, Boolean search is exciting, easy, and more effective than semantic search.

What do I know about any of this?

I’ve evaluated, implemented and used extended Boolean search solutions as well as semantic search solutions. In addition to using them myself on a regular basis, I help 100’s of recruiters use them effectively to find the right people for 1,000’s of real positions. From my practical hands-on experience, I can tell you that sometimes semantic search produces very good results – sometimes it doesn’t. Sounds similar to Boolean, yes?

To all of the “Boolean Bashers” out there – you’re missing the point.

The effectiveness of any Boolean search has more to do with more to do with the person writing the queries and the sources being searched and less to nothing to do with Boolean logic and search syntax

Let’s remember what the goal of sourcing is – to easily find and successfully engage people who are highly likely to be the right match for the roles being sourced/recruited for.

The ultimate sourcing solution would parse resumes and profiles into highly structured data that could be searched via semantic search (autopilot) and extended Boolean (manual control) to ensure that any user could quickly find the right people under any circumstance.

I’m honestly not sure why anyone believes sourcing solutions have to leverage semantic search and exclude Boolean/extended Boolean search capability.

Using Extended Boolean to Achieve Semantic Search in Sourcing

When it comes to sourcing and recruiting, semantic search is perhaps the most powerful way to quickly find people who have experience you’re looking for.

Now, I am not talking about black box semantic search (e.g., Google, Monster’s 6Sense, etc.).

I’m referring to user-defined semantic search, where you tell a search engine exactly what you want with your query, and the search engine doesn’t try to “understand” your search terms or “figure out” what you mean through taxonomiesRDFa, keyword to concept mapping, graph patterns, entity extraction, fuzzy logic, etc.

If you’re not very familiar with semantic search (for sourcing – not search engines), I strongly suggest you read my comprehensive article from January 2012 on the subject: The Guide to Semantic Search for Sourcing and Recruiting. Continue reading

100+ Free Sourcing & Recruiting Tools, Guides, and Resources

 

It’s been a LONG time coming, but I finally got around to updating my free sourcing & recruiting tools, guides and resources page where I now keep a current list of the best of my work all in one place for easy bookmarking and reference.

You can find it here on my main page:

 

Here is where you can find all of the best of my Boolean Black belt content all in one place - free sourcing and recruiting how-to guides, tools, presentations, and videos - be sure to bookmark it, and if you're feeling  friendly, tweet it, share it on LinkedIn and/or +1 it on Google Plus.  Many thanks!

 

Additionally, I thought I might as well put all of my best work all in one blog post as well – over 110 of my articles in one place for easy referencing!

My blog is a pursuit of passion and not of profit – if you’ve ever found anything I’ve written helpful to you, all I ask is that you tweet this out, share it on LinkedIn, like it on Facebook, or give this a +1 on Google.

Many thanks for your readership and support – please pay it forward to someone who can benefit.

Big Data, Analytics and Moneyball Recruiting

Big Data, Data Science and Moneyball Recruiting

The Moneyball Recruiting Opportunity: Analytics and Big Data

Human Capital Data is Sexy – and Sourcing is the Sexiest job in HR/Recruiting! 

Is Sourcing Dead? No! Here’s the Future of Sourcing

The End of Sourcing 1.0 and the Evolution of Sourcing 2.0

How to Find Email Addresses

How to Use Gmail and Rapportive to Find Almost Anyone’s Email Address

Social Discovery

2 Very Cool and Free Social Discovery Tools: Falcon and TalentBin

Talent Communities

The Often Overlooked Problem with Talent Communities

Lean / Just-In-Time Recruiting / Talent Pipelines

What is Lean, Just-In-Time Recruiting?

Lean Recruiting & Just-In-Time Talent Acquisition Part 1

Lean Recruiting & Just-In-Time Talent Acquisition Part 2

Lean Recruiting & Just-In-Time Talent Acquisition Part 3

Lean Recruiting & Just-In-Time Talent Acquisition Part 4

The Passive Candidate Pipeline Problem

Semantic Search

What is Semantic Search and How Can it Be Used for Sourcing and Recruiting?

Sourcing and Search: Man vs. Machine/Artificial Intelligence – My SourceCon Keynote

Why Sourcers Won’t Be Replaced By Watson/Machine Learning Algorithms Any Time Soon

Diversity Sourcing

How to Perform Diversity Sourcing on LinkedIn – Including Specific Boolean Search Strings

How to Use Facebook’s Graph Search for Diversity Sourcing

Social Recruiting

How to Find People to Recruit on Twitter using Followerwonk & Google + Bing X-Ray Search

Google Plus Search Guide: How to Search and Find People on Google Plus

Facebook’s Graph Search Makes it Ridiculously Easy to Find Anyone

How to Effectively Source Talent on Social Networks – It Requires Non-Standard Search Terms!

How a Recruiter Made 3 Hires on Twitter in Six Weeks!

Twitter 101 for Sourcers and Recruiters

Anti-Social Recruiting

How Social Recruiting has NOT Changed Recruiting

Social Recruiting – Beyond the Hype

What Social Recruiting is NOT

Sourcing Social Media Requires Outside the Box Thinking

Social Networking Sites vs. Job Boards

LinkedIn Sourcing and Recruiting

Sourcing and Searching LinkedIn: Beyond the Basics – SourceCon Dallas 2012

LinkedIn’s Dark Matter – Profiles You Cannot Find

How to Get a Higher LinkedIn InMail Response Rate

The Most Effective Way to X-Ray Search LinkedIn

LinkedIn Catfish: Fake Profiles, Real People, or Just Fake Photos?

LinkedIn Search: Drive it Like you Stole It – 8 Minute Video of My LinkedIn Presentation in Toronto

How to Search LinkedIn and Control Years of Experience

How to Quickly and Effectively Grow Your LinkedIn Network

How to View the Full Profiles of our 3rd Degree Connections on LinkedIn for Free

How to Find and Identify Active Job Seekers on LinkedIn

LinkedIn Profile Search Engine Optimization

Free LinkedIn Profile Optimization and Job Seeker Advice

Do Recruiters Ruin LinkedIn?

The 50 Largest LinkedIn Groups

How to See Full Names of 3rd Degree LinkedIn Connections for Free

How I Search LinkedIn to Find People

LinkedIn’s Undocumented Search Operator

Does LinkedIn Offer Recruiters any Competitive Advantage?

Have You Analyzed the Value of Your LinkedIn Network?

Where Do YOU Rank In LinkedIn Search Results?

What is the Total Number of LinkedIn Members?

Beware When Searching LinkedIn By Company Name

LinkedIn Sourcing Challenge

How to Search for Top Students and GPA’s on LinkedIn

What’s the Best Way to Search LinkedIn for People in Specific Industries?

18 LinkedIn Apps, Tools and Resources

LinkedIn Search: What it Could be and Should be

How to Search Across Multiple Countries on LinkedIn

Private and Out of Network Search Results on LinkedIn

How to “Unlock” and view “Private” LinkedIn Profiles

Searching LinkedIn for Free – The Differences Between Internal and X-Ray Searching

Sourcing and Boolean Search

Basic Boolean Search Operators and Query Modifiers Explained

How to Find Resumes On the Internet with Google

Challenging Google Resume Search Assumptions

Don’t be a Sourcing Snob

The Top 15 Talent Sourcing Mistakes

Why Boolean Search is Such a Big Deal in Recruiting

How to Become a World Class Sourcer

Enough with the Exotic Sourcing Already – What’s Practical and What Works

Sourcing is So Much More than Tips, Tricks, Hacks, and Google

How to Find, Hire, Train, and Build a Sourcing Team – SourceCon 2013

How to Use Excel to Automatically Build Boolean Search Strings

The Current and Future State of Sourcing

Why So Many People Stink at Searching

Is your ATS a Black Hole or a Diamond Mine?

How to Find Bilingual Professionals with Boolean Search Strings

How to Best Use Resume Search Aggregators

How to Convert Quotation Marks in Microsoft Word for Boolean Search

Boolean Search, Referral Recruiting and Source of Hire

The Critical Factors Behind Sourcing ROI

What is a “Boolean Black Belt?”

Beyond Basic Boolean Search: Proximity and Weighting

Why Sourcing is Superior to Posting Jobs for Talent

The Future of Sourcing and Talent Identification

Sourcing is an Investigative and Iterative Process

Beyond Boolean Search: Human Capital Information Retrieval

Do you Speak Boolean?

Is Recruiting Top Talent Really Your Company’s Top Priority?

Sourcing is NOT an Entry Level Function

Boolean Search Beyond Google

The Internet Has Free Resumes. So What?

How to Search Spoke, Zoominfo and Jigsaw for Free

Job Boards vs. Social Networking Sites

What to Do if Google Thinks You’re Not Human: the Captcha

What if you only had One Source to Find Candidates?

Passive Recruiting is a Myth – It Doesn’t Exist

Sourcing: Separate Role or Integrated Function?

The #1 Mistake in Corporate Recruiting

How I Learned What I Know About Sourcing

Resumes Are Like Wine – They Get Better with Age!

Why Do So Many ATS Vendors Offer Such Poor Search Functionality?

Do Candidates Really Want a Relationship with their recruiter?

Recruiting: Art or Science?

What to Consider When Creating or Selecting Effective Sourcing Training – SourceCon NYC

The Sourcer’s Fallacy

Sourcing Challenge – Monster vs. Google – Round 1

Sourcing Challenge – Monster vs. Google – Round 2

Do You Have the Proper Perspective in Recruiting?

Are You a Clueless Recruiter?

Job Boards and Candidate Quality – Challenging Popular Assumptions

When it Comes to Sourcing – All Sources Are Not Created Equal

Boolean Search String Experiments

Boolean Search String Experiment #1

Boolean Search String Experiment #1 Follow Up

Boolean Search String Experiment #2

 

The Guide to Semantic Search for Sourcing and Recruiting

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.” Continue reading

Talent Sourcing: Man vs. AI/Black Box Semantic Search

Back in March 2010, I had the distinct honor of delivering the keynote presentation at SourceCon on the topic of resume search and match solutions claiming to use artificial intelligence in comparison with people using their natural intelligence for talent discovery and identification.

Now that nearly 2 years has passed, and given that in that time I’ve had even more hands-on experience with a number of the top AI/semantic search applications available (I won’t be naming names, sorry), I decided it was time to revisit the topic which I am very passionate about.

If you’ve ever been curious about semantic search applications that “do the work for you” when it comes to finding potential candidates, you’re in the right place, because I’ve updated the slide deck and published it to Slideshare. Here’s what you’ll find in the 86 slide presentation:

  • A deep dive into the deceptively simple challenge of sourcing talent via human capital data (resumes, social network profiles, etc.)
  • How resume and LinkedIn profile sourcing and matching solutions claiming to use artificial intelligence, semantic search, and NLP actually work and achieve their claims
  • The pros, cons, and limitations of automated/black box matching solutions
  • An insightful (and funny!) video of Dr. Michio Kaku and his thoughts on the limitations of artificial intelligence
  • Examples of what sourcers and recruiters can do that even the most advanced automated search and match algorithms can’t do
  • The concept of Human Capital Data Information Retrieval and Analysis (HCDIR & A)
  • Boolean and extended Boolean
  • Semantic search
  • Dynamic inference
  • Dark Matter resumes and social network profiles
  • What I believe to be the ideal resume search and matching solution
Enjoy, and let me know your thoughts.

Why So Many People Stink at Searching

The trouble with search today is that people put too much trust in search engines – online, resume, social, or otherwise.

I can certainly understand and appreciate why people and companies would want to try and create search engines and solutions that “do the work for you,” but unfortunately the “work” being referenced here is thinking.

I read an article by Clive Thompson in Wired magazine the other day titled, “Why Johnny Can’t Search,” and the author opens up with the common assumption that young people tend to be tech-savvy.

Interestingly, although Generation Z is also known as the “Internet Generation” and is comprised of “digital natives,” they apparently aren’t very good at online search.

The article cites a few studies, including one in which a group of college students were asked to use Google to look up the answers to a handful of questions. The researchers found that the students tended to rely on the top results.

Then the researchers changed the order of the results for some of the students in the experiment.  More often than not, they still went with the (falsely) top-ranked pages.

The professor who ran the experiment concluded that “students aren’t assessing information sources on their own merit—they’re putting too much trust in the machine.”

I believe that the vast majority of people put too much trust in the machine – whether it be Google, LinkedIn, Monster, or their ATS.

Trusting top search results certainly isn’t limited to Gen Z – I believe it is a much more widespread issue, which is only exacerbated by “intelligent” search engines and applications using semantic search and NLP that lull searchers into the false sense of security that the search engine “knows” what they’re looking for. Continue reading

Bing’s Semantic Search, Phonetics and Undocumented Operator

I was recently performing some searches on Bing and came across something curious that I had never noticed before.

I’m not exactly sure if what I found is new or simply something I’ve overlooked in the past. I updated Twitter with “Did you know that Bing supports the + query modifier?” on November 10th, wondering if it was something that other people knew about.

I only received a few responses, including a couple from noted sourcing luminaries, and the consensus was that I didn’t find anything because it wasn’t documented anywhere and they could not get it to work.

However, the +/Plus sign does in fact work when searching Bing – just not like it used to in Google.

It’s always a little exciting to think you are one of the first people to stumble across something most people don’t know about, although I won’t get my hopes up that I’m the only person outside of some folks at Microsoft who’s ever figured out that Bing supports the +/Plus sign in searches.

This discovery also led me to proof of Bing leveraging semantic and phonetic searchContinue reading

What is a Boolean Black Belt Anyway?

I’ve been blogging nearly 3 years now, and I realized I’ve never come out and actually defined the term “Boolean Black Belt.”

The concept seems pretty self explanatory, but there has been at least 1 person who’s taken the opportunity to point out (and gain some traffic in the process – but it’s all good!) that it could be perceived as a bit of an oxymoron to be an “expert” in something as simple as 3 Boolean operators.

Interestingly, however, I’ve found that most sourcers and recruiters don’t even fully exploit the various powers of the OR and NOT operators – not even close.

So what is a “Boolean Black Belt” anyway? Continue reading

Beyond Boolean Search: Proximity and Weighting

Beyond Basic Boolean

Most sourcing, recruiting, and staffing professionals are familiar with the basic Boolean operators of AND, OR, and NOT. However, I have found that few are familiar with what some refer to as “extended” Boolean functionality, such as proximity search and term weighting.

Proximity and term weighting, where supported, are not actually logical (Boolean) operators – they are more accurately referred to as text or content operators.

Whatever you call them – extended Boolean or text operators – they offer sourcers and recruiters significantly more control, power and precision when executing searches, and in the hands of an expert, they can enable semantic search. Continue reading

Sourcers and Recruiters – Don’t Fear Watson or Semantic Search

I’ve read a few articles recently talking about IBM’s Watson and how the technology they developed may be the harbinger of unemployment for people in many professions.

Here’s one from Fortune magazine, asking if IBM’s Watson will put your job in jeopardy.

Here’s another suggesting that those who train others in Internet, social media, ATS, and resume database sourcing techniques and strategies will be eventually eliminated by semantic search solutions.

Watson Winning at Jeopardy isn’t Surprising

First, let’s first recognize that it’s an apples to oranges comparison between Jeopardy and sourcing/recruiting. Continue reading