Employee Engagement based on Organizational Psychology and Engagement Analytics

Tennis legend Rafael Nadal in his auto biography writes

“Before the start of every game I place my two large energy drink bottles down at my feet, diagonally aimed at the court. Is it a superstition?, of course not, else why would I keep repeating the same thing irrespective of a win or defeat.

Through this gesture I am actually ordering my surroundings to match the order I seek in my own head” This gives me a feeling of control over my environment, for me it’s the singular most important factor for being mentally “engaged” in any match!


“A feeling of control over our immediate environment”. Human engagement, a complex emotional state and carries multiple connotation. But doesn’t the tennis legend nail the core essence?

Amusingly, the Oxford dictionary focuses on the term engagement in reference to marital relations and in this context its meaning is closer to “commitment rather than control”, hopefully! , but be as it may that definition too is only a part of its essence.

A sufficiently encompassing technical definition from an organizational psychology prospective is generally accepted as

“Quantifying human involvement towards defined objectives”. Within the scope of this definition a host of influencing factors could be accommodated, provided the objectives are well defined in the first place and involvement can be quantified, does that hold good for HR?


Let’s explore! Engagement through the eyes of HR aka “Employee Engagement”

Engagement in context to HR

Josh Bersin says “employee engagement is paramount to attracting and retaining talent and remaining competitive in the global market. Research shows a direct link between employee engagement and corporate performance”

Yes of course, the crux of engagement in HR needs to be centric around employee productivity; bills need to be paid, sans doute Monsieur Bersin!

But there is also an interesting counter point here

Global pioneer of workforce analytics Greta Roberts says “engagement is not Performance and there could be dangerous correlations, it’s a tricky metric”

 Possible, provided the hypothesis of no or negative correlation (against productivity) is formed after a thorough analysis, followed by long term observation. This is often an accepted constraint in organizational psychology/HR and sure Greta Roberts is advocating the same here.

The overwhelming majority does advocate a strong relationship. American Business Magazine writesResearch has shown employees who identified themselves as happy in their positions are productive 80 percent of the time at work. Comparatively, employees who identified themselves as unhappy were only productive 40 percent of the time.”

Employee Engagement is the soul of HR and a human cultural aspect applied to business, scoring it against short term business productivity may limit its scope and give a false hypothesis.

Estimating Employee Engagement

Maslow’s theory (hierarchy of needs) is an interesting starting point. Many of us are familiar with this through our business management courses. This time tested theory of “human psychology” provides key insights for understanding human behavior in the workplace.

All the six aspects of the pyramid manifest in some form within the course of the professional carrier of employees and their specific needs within the workplace.

Interestingly these aspects could even manifest differently for star performers, senior level employees or specific personality types. Individuals might have different priorities, perceived status quo and rate the same aspects in the engagement survey differently and it’s useful to identify and study these subgroups.

2017-02-04 16_46_50-Untitled 1 - OpenOffice.org Impress - Copy.png

A traditional approach has been to accumulate survey data on factors estimated to influence employee engagement levels and then calculate metrics/ ratios for evaluation of engagement health. Any hypothesis for improvement initiatives are derived via variance (survey ratings) between different individuals and/or same individuals at different periods.

Key interest survey points have been centric around individual goals, personal space, work life balance, clarity of mandate, transparent assessments and judgments, channels of communication, compensation and benefits, carrier path, work recognition etc.

A process characteristic or component that has a direct effect on whether the overall process is perceived by the employee engagement (in this case) to be of acceptable quality. Identification of specific, measurable critical to quality (CTQ) characteristics is essential for meaningful and measurable business process improvement.

Below shows the traditional flowchart to determine the CTQ for employee engagement.

2017-02-04 13_30_41-Untitled 1 - OpenOffice.org Impress.png

Times are changing, engagement initiatives need to be viewed from a continuous process improvement perspective, for instance the Six Sigma or CMMI point of view.

2017-02-04 15_10_00-Untitled 1.odp - OpenOffice.org Impress.png

Above shows a process flow of data-driven Employee Engagement.

Andrew Marritt writes “Perceptions change over time. As analysts we built a systems dynamics model for engagement and plugged our data in. We can therefore use it as a management simulator to understand what we need to change to improve what we care about engagement.

“Observations spread over a time frame”. In statistical terms what Andrew refers to here is centric around a periodic paired t test.

In addition to these ideas, there is also a lot of inherent disparity in the nature these factors for instance “work life balance” and “carrier growth avenues” and it might be a good experimental idea to reduce all possible factors them into principal components (via statistical PCA analysis or clustering).

Such computational approaches could be employed to gather deep insights from a multitude of angles. Finally one size fits all. Re-engineering the HR policies based on the above findings should ideally be specific to identified groups and their behavioral patterns vis a vis organizational goals.

New Ideas & research pertaining to engagement in HR

An evolving idea is that the estimation of the implicit benefits like health improvement of employees, happiness index of employees, variances in grievances and legal cases, company brand value, may not be necessarily be correlated with short term employee productivity and needs to be observed long term

A 2012 review of more than 200 studies found a connection between positive psychological attributes, such as happiness, optimism and life satisfaction, and a lowered risk of cardiovascular disease.

– Psychological Bulletin.”

Josh Bersin saysengagement programmers help employees perform better in their daily jobs, improve their career planning and help them become happier and more engaged employees. re-imbursement for hourly workers and early career management programs are becoming popular again.”

These aspects may also have implicit benefits in terms of reducing long term attrition, improvement in referral programs, higher glass door rating (company and HR brand value) and other long term hidden benefits.

The below diagram used in this article shows the deploying Engagement Analytics over time period. From Proof of concept till establishing Analytics in an organization or culture.

2017-02-04 13_00_27-Untitled 2 - OpenOffice.org Impress - Copy.png

Let’s also explore a few advanced statistical techniques that can be periodically applied to engagement survey data. These are typically used by practitioners in organizational psychology for deep analysis and can be seamlessly adopted to HR. It is handy for HR to have a high level overview.

HR Engagement Survey Data Challenges.

 So how do the HR Data Analysts/ Organizational Psychology Analyst keep themselves busy?

  • Does HR have a hunch of many hidden subgroups of employees within the organization (different scoring patterns in the engagement survey) – Discriminant Analysis
  • HR needs to know the engagement survey factors that correlate with each other and with “employee productivity or even a third explanatory factor- Deep insights required – Factor analysis, Principal component analysis
  • HR needs to check variance (variability) of identified factors in order to find its relevance or compare same surveys conducted at different times – ANOVA/MANOVA/T test/paired t test to the rescue
  • Based on findings HR needs to progressively field test new ideas in employee engagement and predict its impact – DOE (factorial design of experiments), period review via ordinal logistic regression
  • HR needs to tap deep insights into the employee mindset– open ended descriptive answer based questions and insights via deep NLP (natural language processing) analysis, trust me this can get truly deep!
  • Innovation – design creative ratios (an HR Statistical analyst can get really creative here), metrics and employee engagement, gamification of the workplace

Employee engagement surveys are centric around questions like iteration, feedbacks, job alignment; clarity of mandate, work life balance, but a lot more can be accommodated

Summing Up Employee Engagement

It’s critical to take a balanced, long term approach to employee engagement and asses it from holistic prospective and not short term productivity alone.

The core idea employee engagement analysis is to keep employees invested in the business and also keep HR relevant and empowered within the organization itself.

It’s important to look out for over-complexity emphasize on actionable intelligence and ease of implementation and maintain proper and timely records.

The Ethos and culture of the very origination is based is on the idea of engagement and it’s the primary responsibility of HR to be its guardian, exactly what engaged us to write this piece

Look forward to continued engagement.


Contributed by Raja Sengupta & Soumyasanto Sen

Raja Sengupta is a Data Scientist, Statistician, and Researcher on Computational Linguistics (specialized for HR). he has 17+ years of research and consulting experience in the entire spectrum of applied statistics, analytics, Six Sigma, programming, and NLP. This includes experience in project management, operational research and Six Sigma in HR/Organizational psychology.


Soumyasanto Sen

Soumyasanto Sen is a professionally Consultant/Manager/Advisor/Investor in HR Tech. He has 12+ years of experiences focusing on Strategies, Analytics, Cloud, UX, Security, Integration, and Entrepreneurship in Digital HR Transformation.



Original Post on Analytics in HR


Dealing with Toxic Feedback in the Virtual Workplace

Toxic Feedback in the Virtual Workplace – What Gamers Have to Say

Today 37% of US workers have worked virtually. In a survey by SHRM, 83% of HR professionals predicted this number would increase in the next five years. While this option brings a lot of opportunities to both employers and employees (a bigger talent pool to choose from, better work/life balance, etc), the virtual workplace also holds new challenges for managers, including rethinking the way they encourage collaboration and resolve office conflicts.

Few realize that gaming presents a wealth of knowledge to better understand how collaboration and feedback work in virtual teams. Games provide continuous, real-time feedback. You win, you lose, you level up and feel a sense of satisfaction when you’ve improved. In a thought provoking TEDTalk, game designer Jane McGonigal explains that gamers create strong social relationships because many games, such as World of Warcraft, encourage collaboration to complete a mission. However, much like in the physical workplace, toxic feedback can also discourage teamwork.

Lessons from Gamers

In Fortune’s top fifteen best places to work, Riot Games is a leader in the industry for employee satisfaction. Riot uses annual 360-degree reviews, along with regular one-on-ones to engage and develop employees. They haven’t only encouraged a strong feedback culture in the workplace, but also in their games. When the company found that players were exchanging a high amount of toxic feedback in their hit game, League of Legends, they began conducting innovative new experiments into the impact of positive and negative feedback within teams. This virtual world created the perfect opportunity for psychologists to experiment with ways of influencing positive behaviors and norms.

In the gaming world, toxicity is the term used for poorly constructed and highly offensive feedback. According to Jeffrey Lin, Riot saw this as a major problem. Although only 3% of players regularly use toxic language, everyone has their bad days. In a game with ten people, there’s bound to be someone in a bad mood, increasing the likelihood of toxicity in each game. It was found that 81.7% of games had negative feedback in cross team chats. When players vented their emotions using toxic language, performance across the team diminished significantly.

Riot began using three methods to rehabilitate players. The first was to turn off a player’s chat logs when they were using toxic language and send them a notification. Toxic language decreased by 32.7% in one week. Second, it held online tribunals in which gamers were able to read chats by those reported for toxic behavior and vote on appropriate punishments (banning for x days). This gave the community more ownership in the process of creating positive norms.

Interestingly, the biggest impact was when they sent these players ‘reform cards’. Some players were surprised when they reread their own comments and the reactions they received from other players. Not realizing the impact of their words on the rest of the team, 70% took steps to reform their behavior.

The third strategy they experimented with was to prime players to behave in certain ways by giving them tips in different colors (red, blue or white). The biggest impact was seen when using a combination of tips on negatives outcomes (such as “Teammates perform worse if you harass them after a mistake”) in red and providing positive outcome tips (such as “Players who cooperate with their teammates win 31% more games”) in blue.

Applying these lessons to the workplace

In an interview with Alexander Brazie, former game designer at Riot Games and Blizzard, we discussed why feedback is so important. Even in the game industry, he explained that people working in different areas have different ways of speaking. A programer and a designer might use completely different argumentation skills, often creating misunderstandings. When not addressed, misunderstandings can fuel deeper conflicts.

On League of Legends, Brazie explained, “Games get you emotionally hooked. People in emotionally charged states are generally not the best people to be giving feedback.” Similarly, when emotionally charged conflicts occur in the workplace, employees may use toxic language without realizing the damaging consequences. In a virtual workplace these conflicts can be magnified as people cannot use facial expressions or body language to gauge emotions. If you’re planning on moving towards telecommuting, it’s important that employees first learn how to give feedback constructively.

One-on-ones can have a major impact. Brazie explained, “If you really want to solve a problem you first need to give your employees the tools and experience they need to communicate on less stressful topics.” His manager at Blizzard took time to work with him on reforming his communication style and this knowledge has stayed with him throughout his career. At Riot, one-on-ones occur on a weekly basis and are, in Brazie’s opinion, the most helpful aspect of its performance management strategy today. With the insights from their experiments, Riot is now considering making real time feedback a more continuous process beyond their one-on-ones to help develop positive workplace behaviors.

Brazie is now a game design consultant for Xelnath Enterprises, specializing in game design analysis and cross-disciplinary conflict resolution. When a conflict occurs, he suggests that, “the best way to approach the situation is to start off with establishing goals you have in common. You will find you actually agree with someone 80% of the way, so having this structure can actually help you to overcome challenges.”

Solutions for your company

In League of Legends, a strong motivating factor in behavioral change was when toxic players understood the negative impact their comments had on the team’s success rate. On the flip side, players who collaborated with their teammates won 31% more games.

Focusing on the positive side of online feedback, Riot implemented an ‘Honor Initiative’ allowing players to award points to teammates and opponents who demonstrate helpful or friendly behavior. This addition has become wildly popular and is expected to incentivize players to follow the new social norms created online. Riot is even giving badges and other awards to increase the visibility of these players.

Similarly, some companies encourage collaboration by separating performance reviews from promotions, instead linking them to the quality of feedback employees give each other. Separating bonuses from individual performance also takes the pressure off receiving feedback. Others have brought the real time feedback experienced in games to the workplace through new mobile apps aimed at increasing timely and continuous micro feedback. While it’s impossible to put people on mute when they’re having a bad day, this approach emphasizes that it’s not only about giving more feedback, but learning to give feedback the right way.

This article has been written by Steffen MaierCo-Founder of Impraise and originally published in The HR Tech Weekly® blog.

Original Post

Employer Brand: Base it on a Thought Leadership Strategy

Why is thought leadership so important for a modern organization? Because it’s at the very core of social selling and attracting the best candidates to work with and for us. It’s employer branding at its best! And, ultimately, it’s the foundation of an organization’s success and growth.

Thought leadership strategy is not just part of the content marketing strategy, although it is also that. Thought leadership strategy and its execution require you to help your employees become the personal brands they already are, even if they don’t consider themselves to be brands, or the employee advocates that you want them to be but that they don’t necessarily want to become.

Remember, the best employer brands are built on employee brands!

I’m not talking about influencer marketing here, but a move to a much more strategic approach and overall strategy rather than content marketing with internal influencers. It’s about building long-term image strategically as an organization that consists of the top minds within our industry and beyond. No campaigns, no external influencers, but internal, long-term commitment to building personal brands for our top specialists, helping them become the brands they already are and enabling them to reach larger audiences in a more strategic manner.

Start by asking yourself, “If I were a customer, what kind of information would I be looking for? What would add (value) to my knowledge and influence the decision-making process?” And there it is, the foundation of the content part of your new strategy! Answering this shows you know what kind of information you need to focus on. That’s the quick and dirty approach.

Choose your media, where you will reach your potential target audience, what they are interested in, and how to attract their interest and reactions. You might even want to build buying personas for your target audience.


But the Internet is full of noise. We could produce huge amounts of material that no one finds or is interested in. It sometimes seems as though half the world has gone crazy on content marketing, creating enormous masses of content, just content.

Instead, put your effort into distribution, that is, how and where people find your content! Remember, it’s not quantity, but quality, that builds thought leadership, but even the best content is worthless if no one can find it.

Content is always more credible when it comes from an employee, a specialist, rather than via corporate official accounts or the CEO. It needs to be personal and one’s own creation, not written by a ghost writer or the comms team. The author needs to stand behind the content.

Focus on these four things:

1. Content – visuals and quality of thinking, but also confidence and risk-taking (visionary content). And it’s quality over quantity.

2. Reach – networks or media? Should you build your own following and media or use existing communities to build your brand?

3. Consistency – requires time and dedication. Quick wins are rare but possible.

4. Novelty – your content must (often, not always) provide new insights, ideas, provoke readers’ thoughts in a way that hopefully makes them react – like, share, comment or follow – and eventually buy your services or consult you when making decisions.

Thought Leadership Strategy Leans Heavily on Employee Advocacy


Thought leadership strategy needs:

  • Buy-in from top management, as it requires a new kind of openness and sharing of content that some may consider business-critical. It also takes time – it doesn’t happen overnight. And it helps if the top management leads by example.
  • Buy-in from employees, as they need to be the ones creating the content – with help, support and even training from the marcomms team. Passion and true love for the line of work and the company never hurt thought leadership. It’s employee advocacy on steroids!
  • A certain type of company culture. In an organization where talking about customer cases or showcasing personal expertise are prohibited, or where communications have been strictly reserved for those at the top management level or in the comms team, it takes time to create a culture of openness, employee advocacy, and engagement. Culture is grown. It can’t be brought in just like that, ready to roll when we say so.
  • Collaboration within the organization to make it count. Specialists, our top minds, can’t make it alone. Even if they have the credibility, they often don’t know the right media for sharing the content, may not understand the strategy and reasoning (the big picture), or don’t have the budget or opportunity to work on content creation. The marcomms team doesn’t have the credibility, but it does have the understanding of the media, and often has the budget for it. The sales team is driven by numbers, not image, so they need instant feedback in the form of leads and customers, and they don’t have the budget or understanding of the media. The top managers aren’t credible, as they don’t have the skills, nor do they understand the media, but they sit on the budget and understand the strategic value of thought leadership. Therefore everyone needs to collaborate to build an efficient thought leadership strategy for years to come and markets to conquer. None of them can do it alone.
  • Thought leadership strategy feeds on ideas, innovation, novel ways of working, processes and technologies. You can’t be a thought leader with ideas that your competitors have recycled year after year. You need to think out of the box and dare to say it out loud.
  • Last but not least, thought leadership strategy needs to be aligned with overall business strategy: what do we want to sell, to whom, when, where, at what price, and what next?

Thought Leadership Is All about Building Pull Instead of Having to Push

ITSMA came up with great metrics to measure the thought leadership impact: Reputation, Relationships, and Revenue. That’s all. Easier said than measured, but doable.

Have you noticed that some of the top brands have already started implementing thought leadership strategies? Some of them already do this, though not from the employer branding point of view, but for social selling.

So now let’s take full advantage of it. Employees are the true foundation of an organization’s growth and success.


This article has been written by Tom Laine and originally published in WISP blog.

Original Post

About the author:

tom-laineTom Laine is considered to be one of the most visible and experienced social media and digital recruiters in Europe, having founded his first social media startup in 1999, and a social recruiting agency in 2009 – the first ever in the Nordics. Before founding his own agency, Tom worked as a Channel Campaign Manager for Oracle in Denmark; previously, he lived in London, where he worked at a variety of recruiting agencies and search firms.

After successfully selling his agency to a market leader, Tom has written and published several books on social media and emerging technology. He currently advises a global portfolio of clients on social recruiting, employer branding and recruitment marketing as a consultant and trainer. You can learn more about Tom by visiting his personal website, http://www.TomLaine.com.

Follow Tom on Twitter @LaineTom or connect with him on LinkedIn http://www.linkedin.com/in/tomlaine

How Natural Language Processing can empower Human Resources

Natural language processing is an ever-growing interest area in the analytics application spectrum and is relevant to HR. In fact, it can revolutionize the quality of insights. In this article, we will explain you how.

Natural language processing has a significant relevance to HR

Did you know that text analysis has been the most prevalent productivity tool over the past 3 decades or so for HR? It is very familiar to HR.

HR has been using Boolean keyword searches for identifying good resumes/ job applications for a long time already. However, often with unpredictable and humorous results.

Natural language processing (NLP) takes text analysis to the much higher level of detail, granularity, and accuracy. Acute insights from NLP were a technological constraint in the past but there have been major strides of late. This has aided by the development of distributed computing and from the intense research in NLP applications by academic and professional bodies around the world.

The essence of people function lies in an effective analysis of communication and natural language is the most prevalent medium of human communication. However, the scope of NLP in people function needs to be spearheading by operational HR alone.

Most HR business engagement generates high volumes of natural language, which is unstructured data. Think about areas like recruitment, employee feedback, surveys, appraisals, learning, legal cases, counseling etc.

Additionally, legacy HR processes and forms can be re-engineered to accumulate ever increasing volumes of natural language data. Via an active policy of audio recording & transcribing or even a slight redesign of various HR processes forms/surveys/applications.

Key benefits for HR with reference to natural language processing

Benefits are many, corresponding to varying levels of engagement and investment by HR.

It starts from generic text analytics (sentiment analysis). Goes to advanced insights (via computational linguistics models) and can even include potential semi-automation.

Once implemented, such services can be delivering via APIs and database connectivity. Or even from standalone client based systems. Google and Microsoft are prime big player examples in the API NLP space.


How do the insights from natural language processing analysis impact HR?

HR specific NLP analysis, with varying and often progressive levels of insights not only acts as decision supports (DSS). But also, enable greater accuracy and speed to key HR business processes and improving HR metrics. They also reduce human bias in decision-making application. Examples include resume scoring and survey analysis.

Often NLP systems act as “first or second level filtering” or “hypothesis proofs” to corroborate human decisions in HR

The NLP evolution curves below indicates the needs of text analytics and computational linguistics as it maximizes the business benefits of NLP.


Structured and unstructured data synergize to improve the quality of insights for HR.

For instance, key traditional areas for HR data modeling have been attrition, absenteeism, career paths, compensation & benefits, etc. For such models, the insights gained through NLP can fit in as explanatory variable thereby improving the accuracy of the model.

Usually, HR processes forms like employee survey, feedback, assessments have consisted of several structured data points (check, radio, drop down, slide boxes, etc.). The NLP can be used to further incorporate and capitalize the open answers in this survey. This improves the quality of insights.

Taken together, they both improve metrics of HR processes.

Misinformation with regards to adoption of natural language processing in HR Processes

It is not the case that natural language processing systems replace HR. On the contrary, these systems further empower HR personnel within their organization.

The complexities of human language, communication and dynamic decision making required by HR in the real world is complex. This implies that total automation is impractical and can be downright counterproductive. Machines find it complex to comprehend the finer nuances of human language. Like sarcasm, ambivalence, deformed compliments, passive aggression, regional norms, etc.

An interesting and somewhat parallel comparison is in the case of autopilots and flies by wire systems. They have been around for two decades or more. But never replace humans in cockpits, although in simulation tests they outperform human pilots.

Drones (theoretically pilot-less) are also controlled by a human pilot.

The concept of full automation is completely misplaced. Job losses are actually skill restructuring/ retraining/ realignment program. Not result from automation and may be progressively required.


Bottlenecks in adopting natural language processing to HR

There aren’t many vendors who are only focused on advanced NLP to HR processes yet. Most vendors are text analytics generalists; they may not have in-depth aware of HR specific challenges. OrganizationView is a good example of a dedicated operator in this space and there are a few more.

Other key bottlenecks are HR data security/protection, data accessibility, quality, API integration. The engagement and collaboration programs between HR and IT also have scope for improvement in this area.

Large strides have been made in recent times about the application of NLP to other areas. For instance, NLP enables service providers to process vast amounts of data and make predictions on bankruptcy evaluations and contracts in the legal sector. Script writing is revolutionized using NLP in the entertainment business and now the time is ripe for adoption in HR.

Identified approaches in NLP that are relevant to HR

Operational HR should take the lead and identity relevant application areas within their own organizations. The impact of NLP in HR is likely to depend upon data availability, security, integration, company policy or any other specific business requirements.

Broadly there are three aspects to applying NLP to HR.


1. Types of Generic natural language processing insights (relevant to the HR application context)

  • Sentiment Analysis of HR documents
  • Deep Information Extraction from HR documents
  • Classification/ ranking of HR documents as per business specifications
  • Automated Summation of HR documents (topic discovery)
  • Establishing HR Hypothesis and process improvement (a part of prescriptive analytics)

2. Application areas of natural language processing (within the HR application context)

  • Application/ Resume classification and scoring
  • Appraisal and 360-degree feedback analysis
  • Surveys and feedback analysis
  • Identifying Training, Succession planning
  • Social media content analysis of employees
  • Insights on documented Legal cases/ suits
  • Design and insights about Employee Counseling
  • NLP on virtually any unstructured data within the scope of HR, including transcribed data.

3. Overview of various NLP methodologies employed by vendors (within the HR application context)

  • Statistical Tagging

Statistical tagging offers insights from various levels of granularity starting from basic text classification, sentiment analysis to deep information extraction and topic modeling/ automated summation. Some of the popular information extraction/ topic discovery approaches are Conditional Random Fields, Hidden Markov Models, and LDA.

  • Symbolic Tagging

The HR familiarity with basic Boolean keyword searches to identify good resumes is a very good example of symbolic tagging. But today NLP models like nested, iterative and conditional “regular expressions” can fine tune symbolic tag searches to the deepest possible levels of granularity.

A combination approach of statistical and symbolic tagging is often referred to as a “conditional rules model” within the NLP context. Tailored combinations of “conditional rules models” are typically developed via integrated cohort analysis in collaboration with HR.

This may also help to establish evidence-based HR Hypothesis. And effectively push forward major HR initiatives to the organizational leadership.

A business case of NLP in a key HR process (Hiring)

The basic approach of natural language processing remains more or less the same across all types of unstructured data. However, for the sake of familiarity let’s take the example of resume scoring in Hiring on a large unstructured dataset


Here NLP can help on resume classification, ranking, deep extraction, identification and semi-automation in the hiring process

  • Classify and rank resumes according to their core skills, experience or any other priory. Like desirable skills and professional experience.
  • Classify resumes according to their format styles. Like chronological, reverse chronological, hybrid, skills-based, and qualification based functional based formats.
  • Identifying basic sections of a resume (topic model based on the priority given by HR)
  • Identify gaps in professional/ academic records in resumes
  • Identify potential fraud/ incorrect information and anomalies in resumes
  • Deep information extraction from resumes. For instance combination of professional skills/ education + university rankings + professional experiences + environment and context + international assignments/ location specific + awards/ recognitions + recommendations/ professional network ) via compound “conditional rules models”

Apart from resume/ application scoring, “Conditional rules models” can also help identify complex human language expressions. Like sarcasm, ambivalence, deformed compliments, passive aggression, this might be important for HR surveys, feedbacks, forums, social media data etc.

However, the degrees of accuracy may differ (and it’s an ongoing research area)

In systems where applications/ resumes have semi-structured data points (for example applications received through an online XML form), NLP can act in conjunction with the structured data points (SQL) for improving the quality and accuracy of classifications and inferences.

Once developed, semi-automation can also be applied to NLP models to enable

  • Periodic and automated evaluation of dataset via batch jobs and database procedures/triggers/functions
  • Automated scoring and classification of datasets via above
  • Sending an automated email to shortlisted candidates (for example a test set or interview call) or sending consolidated or specific reports to the HR/Recruitment team.

All these could reduce cost for the recruiter and add more accuracy in candidate screening. The NLP approach can definitely find the better candidates for a job application without any human biases.

Typical services offered by NLP vendors

NLP vendors typically offer a combination of services mentioned above, including summation, topic modeling, and conditional rules models.

However, don’t be fooled. Innovative marketing and promotion schemes might give the impression that there is a variety of computational approaches in NLP among different vendors – even though they are fundamentally the same.

It is therefore important for operational HR to have a good overview and to be able to discern NLP applications relevant to their specific business requirements and constraints

NLP application service delivery might be through API services/ database integration or standalone implementations on clients (windows based installations). Static periodic reporting system (for example process improvement via a six sigma framework) would add advantage here.

The Future…

HR is the prime candidate for adoption of NLP-based technologies, as HR is inherently people-centric and communication-based. HR business processes thus generate vast amounts of natural language data.

This presents an opportunity for HR. It will also enable HR to have greater intelligence and leverage within the organization.

Early adopters and pioneers don’t hesitate to contact us for further engagement!


Contributed by Raja Sengupta & Soumyasanto Sen

Raja Sengupta is a Data Scientist, Statistician, and Researcher on Computational Linguistics (specialized for HR). he has 17+ years of research and consulting experience in the entire spectrum of applied statistics, analytics, Six Sigma, programming, and NLP. This includes experience in project management, operational research and Six Sigma in HR/Organizational psychology.


Soumyasanto Sen

Soumyasanto Sen is a professionally Consultant/Manager/Advisor/Investor in HR Tech. He has 12+ years of experiences focusing on Strategies, Analytics, Cloud, UX, Security, Integration, and Entrepreneurship in Digital HR Transformation.




Original Post on Analytics in HR


Building a Brand for Your Startup

Building a brand for your startup can be very tiresome, especially if your company has been just founded and it doesn’t have regular customers, prospects and leads.


In this article, we’ve listed 4 important tasks each branding process should include.

You’ll learn how to make profiles of your ideal buyers, create your brand’s visual identity, choose the best promotional products and create engaging marketing messages.

Know your audience

Every branding action needs to be tailored for the right audience.

Although you may think you know the crowd which would be interested in purchasing your product, you need to conduct an elaborate research that will give you precise consumer profiles of your targeted audience.

In marketing terms, you need to find a buyer persona for each one of your products or services.

These are fictional and slightly generalized representations of your ideal customers.

The best way to find an ideal buyer persona is to interview the right people and sum up their answers in a persona template.

If you already have customers, try offering them some incentives for taking part in your survey.

Entrepreneurs who have just started their business can hire third-party interviewers or interview their own acquaintances.

Here we listed some of the important categories your interview should cover, together with a few sample questions for each category:

  • Personal demographics – including: age, gender, marital status etc.
  • Role – “What’s your job title?”;
  • Company – “In which industry do you work?” and  “How many people work in your company?”
  • Goals – “How do you plan to elevate your life in the next 5 years?”;
  • Challenges – “What was the most challenging thing you’ve ever done?”;
  • Pastimes – “How many books do you read per month?” and “What’s your favorite blog?”;
  • Shopping preferences – “How do you prefer to interact with vendors?” and “Describe your most recent purchase”;

At the end of the interviewing process, you will have a lot of raw data that needs to be organized.

Find downloadable persona templates online and organize all the information you’ve gathered.

These templates usually have several segments that range from basic demographic info to motivations and behavioral data.

After you run all of the consumer data through the template, you’ll be able to round off your perfect customers’ profiles.


Create your brand’s visual elements


Appealing visual elements are the most essential components of every brand.

If you’ve just founded a startup, the first thing you need to think about is your company’s visual identity, which usually includes color scheme and a logo.

Before you pick your favorite visuals, you should study how different shapes and colors affect consumers’ minds.

DIY entrepreneurs often decide to create their own logo, but we wouldn’t recommend this option unless you’re a professional graphic designer.

Give them something useful


Consumers like free things.

A useful and appealing promotional product allows consumers to recognize your brand and to share it with the rest of the world.

The type of promotional product that will create the biggest buzz for your startup depends on your niche and the consumers you want to attract.

If you’ve already created your ideal customer personas, it’ll be easy to find the perfect product they would use, share and walk around with.

Useful promotional products can be categorized in 2 groups:

  • Products for long-term use – are durable products that last from 1 to 3 years on average;
  • Products for short-term use – are products that are useful only at the given moment, like wet tissues or SIM cards with limited credit;

Promotional products are relatively cheap and come in a variety of options.

You can consider different types of booklet printing, brochures, flyers, cards but also promotional materials such as t-shirts, reusable shopping bags, pens, coasters, key holders…

Use the right words


Your marketing message is usually the first contact consumers have with your business.

Most entrepreneurs want to create a short brand message, like Apple’s “Think Different” or Nike’s “Just Do It!”.

Others make their messages too explanatory, which also makes them bland and weak.

When you’re designing your marketing message, you should use the 4E framework.

  1. Explain – Explain the products and services you’re offering;
  2. Emotion –  Play with consumers’ emotions;
  3. Evoke Questions – Spark consumers’ interest;
  4. Exclude/Include – Target specific groups of consumers with your message;

If you can’t sum all of these criteria in your marketing message, try to include at least some of them.

In the early stages of your company’s development, you should focus on raising consumers’ awareness, which means that your messages will mainly stick to ‘Explain’ criterion, because you need to tell consumers who you are and what you do.

You should also give a special attention to message’s emotion, because people’s buying decisions are rarely based on logic.

Although branding can be very complicated, it’s still the best shortcut to consumers’ trust.

Since products have lifecycles, brands often outlive them and become company’s most valuable asset.

When Tata Motors bought Jaguar and Land Rover company for $2.3 billion, luxury vehicle and SUV brands were more valuable than all other company’s assets combined (including factories, machines, distributers’ network etc.).

Another reason why you should start building your startup’s brand in the early stages of business development.

Original Post




Adrian Tan is CEO of The Resource Group, a boutique HR Consultancy that focuses on helping SMEs. Before this, he was the MD of RecruitPlus which he co-founded in 2004 and led to two HR Vendor of the Year award. He was named the HR Entrepreneur of the Year by SHRI in 2013. He blogs regularly on #Entrepreneurship and #HRTech on adriantan.com.sg.

HR Technology and the “New” Industrial Revolution

The world of work has been shifting and evolving since the Industrial Revolution. We are now experiencing a new shift, and it’s a dramatic one. The Industrial Revolution inspired the creation of child labor laws, but it didn’t stop the progression of power-driven machinery expanding the textile and other industries. Similarly, the growth of the gig economy and on-demand workforce has not slowed, despite the calls for reform from politicians, the NLRB, and the FLSA to enforce labor standards, proper classification and protection.

We are moving away from having one job and staying in it for decades. The “new normal” of our workforce will consist of roughly 50% contingent talent (gig or independent workers) by 2020. The on-demand and gig workforce brings cost-efficiencies, vital skills, fresh perspectives and agility in times of unpredictable global markets and shifting labor demands. Social behavior and the workforce mix have changed the way people work. Workers have created independent “job security” and personal marketability following the Great Recession, wanting flexibility to enable greater life balance; “9:00−5:00” is becoming outdated.


Millennials, who gravitate toward flexible and entrepreneurial careers, will comprise half of the total workforce by 2020. Brick and mortar office space is making way for a digitally connected remote workforce across the globe.

The Talent War is real. Baby Boomers (and their business knowledge) are leaving the workforce at the rate of roughly 10,000 every day. According to the U.S. Bureau of Labor Statistics (BLS), there were 5.0 million job openings at the end of 2014, up 38% from two years ago. Skills shortages are causing delays in hiring and lost revenue.

Nearly half (49%) of employers surveyed by CareerBuilder claim job-specific skills are a scarce commodity; 60% of employers are concerned about the costs associated with delays in filling open positions, with one in four stating they have experienced losses in revenue as a result.

Technology has been dominating the HR and Talent Management space for the past decade – with increasingly widespread adoption occurring in the past year’. The digital talent supply chain, made up of the gig and on-demand workforce, is driving how we find, manage, and engage our total workforce. People with no time but money and people with no money but time can now trade with each other.

Technology is not changing the way we work; the way we work is driving technology. Talent Strategy in the future will engage a technology ecosystem of different platforms handling all aspects of an organization’s workforce. HR is now a strategic partner for organizations and is taking a more innovative role, including driving user adoption of several types of technology platform that cover the full lifecycle of Talent Strategy.

Enter the “new” Industrial Revolution

For Starters… Mobile-friendly designs are crucial: this generation’s talent does EVERYTHING on their phones, across the globe. HR needs to go where the talent is, and today it is on cell phones.

A Day in the Technology-Enabled Life of HR


Workforce Data and Analytics – Workforce data is critical. Today you have access to dashboards covering your total talent landscape (contingent, IC, perm): VMS (Vendor Management System) technology like SimpleVMS captures all your temporary talent data; and RPO (Recruitment Process Outsourcing) like Future Step captures recruitment process data. All these systems can be integrated as these technology platforms are designed with open API, giving you headcount, screening, onboarding, assessment, tracking, and vendor management. This data can be easily shared between departments/divisions; everyone is on the same page.

Talent Sourcing and Vetting – Recruitment networks like Peopleloop provide localized recruitment outsourcing in order to source talent quickly and cost-effectively in any location. Opening IO uses Artificial Intelligence, with robots trained to find suitable candidates according to minimum specifics, using linguistic algorithms to identify patterns within the structure and phrase of a job post to match with potential candidates. Professional recruiters can leverage platforms like Hirabl to track hires presented and determine vacancies, facilitating a proactive approach to hiring.

Worker Training and Retention – Training and development are key to combating the talent shortage and filling talent gaps. Annual performance reviews are obsolete. Companies like HighGround automate and elevate the employment review, development and rewards processes with real-time 360-degree feedback, surveys and interactive platforms. The WISP HR platform provides employee engagement tools to enable higher productivity, motivation, and collaboration.

These are just a few examples. HR Talent Management technology providers will continue to refine their offerings and cannibalize features of other technologies to broaden their platforms and services and capture the most useful functionality.

The key to embracing the “new” Industrial Revolution is not asking “Is this amazing technology?”, but “Is this technology a good match for us?” Execution and simplicity will be key to leveraging these technologies to take your business to the next level, and HR will be at the helm.

This article has been written by Terri Gallagher, she is President/CEO at Gallagher and Consultants and originally published in WISP blog.

Original Post

Good relationships foster employee well-being

In early 2017 we see the growing awareness of the impact wellbeing can have on individuals, businesses and the economy. Along with that, there is a growing interest from the investment community in wellbeing as a leading indicator of financial performance and market value. Many researches during 2016 showed that organisations with effective wellbeing programmes outperform the market because high levels of wellbeing lead to better attraction and retention of talent, lower levels of absenteeism and higher engagement levels.

Wellbeing includes people’s physical and mental health and the social/relationship aspects of their work environment. It includes factors such as how they get on with their manager and colleagues. The company culture is critical to wellbeing: a culture where people feel trusted, valued and respected will engender feelings of wellbeing. Organisations where the culture is poor are more likely to suffer lower levels of wellbeing. So, whilst wellbeing programmes are important, they will be less effective if the organisation’s culture is poor.

Wellbeing is a key driver of engagement so for many employers focusing on employees’ wellbeing is a conscious business decision. If the work/life balance isn’t right, or employees don’t feel respected, valued or that they are treated fairly, they are more likely to become demotivated, disaffected and eventually leave the organisation. To avoid that, organisations have to consider the following aspects:

  • Values and ethical behavior: values and their corresponding behaviors shape an organisation’s culture. A poor cultural fit or weak  values can all affect employees’ sense of belonging, job satisfaction and personal wellbeing;
  • Teamwork: collaboration, as well as being good for productivity and innovation, can help break down silos, increase employees’ sense of worth and create stronger bonds between colleagues;
  • Employee’s relationship with their managers: great managers can balance the technical and soft skills and build trusting relationships with their teams. Bad relationships can make life for employees difficult or even unbearable, leading to staff turnover and the inevitable impact this has on the business.



On one hand, small organisations are more likely to have this kind of emotionally and psychologically healthy environment where wellbeing can flourish. This includes the softer aspects of the workplace, such as team spirit or a sense of “family”, where employees feel valued and supported and where flatter management structures offer more scope for getting involved in decisions and projects.

On the other hand, for large organisations is quite the opposite: a hyperconnected workplace where, despite the proliferation of social and collaboration tools, employees barely know who they meet in the elevator and end up “eating with their Facebook”, and where the executives struggle to spread a culture of shared values and to keep the workforce engaged. Moreover, since ESNs or other collaboration/social tools are part of the problem rather than the solution, what is really needed to foster wellbeing is real human contact.

HR managers should be able to organise frequent events with a small number of attendees: for example, breakfasts before work between the CEO and the employees. This is the best way to foster the creation of new links and good relationships, but, managing something like this would be a nightmare when hundreds of employees are involved and is hard to reach high level of the engagement by using the usual pull-communication.


This article has been taken from the original publication from Woobe Blogs

Original Post