Category Archives: Digitization

A chatbot as live representation of my resume


How to differentiate yourself when sending a resume to a recruiter? I trained a chatbot to respond to the most common questions a recruiter is asking.

To get attention from recruiters nowadays is not easy. Making a decent resume in a 2-page PDF is no longer a skill, nor you can differentiate yourself with it. A complete and neat LinkedIn profile is a must. And online you can find beautiful designed ‘designer resumes’ which makes you wonder why you skipped arts class. Adding ‘creative’ to your skills is not creative any more. Who would hire somebody who says he isn’t creative?

My first attempt to differentiate was via a graphic recording of my resume. It was a technique I learned from Martine of VisualHarvesting.com. You can view the visual representation here. While it is kinda original, it represents the technique and my skills of applying it, but not the skills I want to exhibit to recruiters.

I have experience with digital transformation and facilitating change & innovation in a large international organization, so my resume should reflect that. A bit more ‘innovative’, instead of ‘original’. That’s when the idea of implementing a chatbot came. A chatbot to represent my personal resume. A chatbot that could be a first contact to interview me about my career, strengths, skills, improvement points, etc. I’m sure I’m not the first one to have this idea, but I would like to put it into practice.

Finding a chatbot service

I have a Master in Computer Science and a post-graduate in Software Development, but during my career I grew to more an organizational and policy function. So my Master in IT is a good base to start with, but my developing skills are aged and out of date. So I had to find a chatbot I could deploy without having a server and having to code.

After a quick search, I found Botsify.com. The site promises an AI chatbot without coding and easy integration with Facebook Messenger. If you’re creating a chatbot for your resume, it should be publicly accessible and almost everyone should be on Messenger by now, so that was a no-brainer.

Charlie with Botsify

Botsify was easy to start with and I created a chatbot named Charlie (a nickname my first department head gave me) to represent myself. The first version of Charlie was made to respond to keywords.

Eg. “What are Karel’s strengths?” gave the reply “Karel’s strengths are starting up (change) initiatives, creative and innovative communication, entrepreneurship, public speaking, visualization and his passion & enthusiasm.”

This seemed too easy to be true! And than the first feedback of the testers came in: the chatbot couldn’t understand the intent of the user chatting with it.

Eg. “What does Karel like?” gave the reply “Karel likes making the digital transformation tangible for the employees. He like working with his project team and all the different profiles. He likes to develop training programs. Coming into contact with many different people. He likes the international character of his job too.”.

“What does Karel not like?” gave the same reply, because Charlie still reacted on the keyword ‘like’. Using the keyword ‘not like’ didn’t work on Botsify.

From keywords to phrases

To make the chatbot more human alike, it had to be able to understand intents. Instead of reacting on keywords, I learned Charlie to recognize phrases. To be sure the chatbot would be able to understand the user’s intent, I added multiple formulations.

Eg. “what does Karel want?”, “what is he looking for?”, “what function does he want?”, etc. 

Eg. “What does Karel want?” gave the reply “Karel would like to advise and support organizations in achieving the full benefits of the new technology through change management. He would like to lead a team working on the different components of change activities: an innovative campaign, a talent development program, etc.”

Botsify chatbot

The move from keywords to phrases made the chatbot less responsive. I learned that every user has his own way to formulate a question, some write full sentences, some write with(out) spelling errors, etc. While the chatbot was tested by more and more users, it came clear to me that the AI of Botsify was not ready for it. The slightest difference in formulation or spelling mistake, made the chatbot reply the default “sorry, I don’t understand your message…”.

Enhance user experience

When working with keywords, the intent was not recognized and some answers were not correct, but with phrase recognition a very simple look-a-like question couldn’t be answered. I saw users leaving after a few attempts. To enhance user experience, I created multiple default messages which also contained suggestions for asking the right questions. Also I created a help function and added some buttons with default questions.

If you want to give it a try, go to http://m.me/Norulesjustwords

Note: there’s a limit set at 100 users (all time), so if the chatbot is offline, we reached the limit 🙂

Move to IBM Watson Conversation

When many users use Botsify at the same time, the chatbot was also lagging and responding incorrect, for me this was the final blow. A representation of my resume that wasn’t responding to simple questions doesn’t deliver what it’s made for.

In my search for a new chatbot, I found IBM Watson. With the Watsom Conversation service I was able to create a chatbot in a very short term, and a better one too. The Watson chatbot also works with AI and is rather easy to configure. The big advantage is that Watson’s AI is working and Watson has NLP, Natural Language processing. NLP was the one solution for dealing with different formulations and spelling errors.

Eg. “what are you doing?” is interpreted in the same way as “what is your job”, “what do you do for a living”, etc.

The setup of my new Charlie was started: intents can be added quite easy and with multiple variants. Adding dialogs and testing goes quick too. The chatbot was set up in less than a day!

IBM Watson Conversation

The integration with Facebook Messenger is another story though. While the Watson chatbot is easy to configure, learns better, has AI and NLP, it’s a whole different story offering this service to end users. Linking my Botsify chatbot to Messenger was done in seconds, for Watson I’ve been busy searching for hours, still without any result.

So at the moment of writing, I have a better chatbot, but still need to figure out how to get it online. But I’m not giving up 🙂

Give the first Charlie chatbot a go

In the meanwhile, you can test my first Charlie chatbot at: http://m.me/Norulesjustwords

My full resume can be found here: https://www.linkedin.com/in/karelnijs82/

 

Special thanks to my friends, family and colleagues for testing Charlie! Special thanks to Bert De Sutter for his elaborate feedback!

 

Advertisements
Tagged , , , , , ,

Claim for the Award for the Most Eager To-Be Subscriber of The Economist


There’s social media, omni-channel and customer experience. Three buzzwords of the last decades, together with a portion of stubbornness that make me claim the ‘Award for the Most Eager To-Be Subscriber of The Economist’. Read further to understand my claim.

Last week, while I was scrolling my Facebook feed, I came across of an interesting offer of The Economist: “Get 12 weeks of subscription for only € 20”. For a weekly magazine, that’s quite a good deal to find out if the content is good for you.

I checked out the offer and was looking for the fine print. The catch behind the deal. Would it be an automatic renewal which I couldn’t disable for a year? Or would it be possible to just cancel the subscription after the 12 week try-out period? In Belgium, this is a very common formula, certainly now in the age of declining print media. You get a try-out for a month or longer, and after this period you cancel and try another paper/magazine.

Because I couldn’t find an answer to my question in the fine print, I added my question in the comment section. After a day without a reply, I decided to contact The Economist via Facebook. The Facebook page told that The Economist “responds typically very fast” to messages. That’s perfect, I thought, so I launched my question via Facebook chat. Indeed I got a message immediately, but it was clear I was talking with to an automated reply, maybe already a chat bot? There was nobody on the other side of the line to answer my message. I tried a few times (maybe there’s a time zone difference?), but still no answer, except for the default reply.

No problem, let’s try a more traditional channel: e-mail. I mailed the support desk and received almost immediate a reply. A reply which told me that they couldn’t help me because I had no 8-digit Customer Reference Number (CRN). The received e-mails without a CRN, login email and news email in the contents “would not reach us”. Sounds like a catch-22, doesn’t it?

I couldn’t believe this, so I retried with a message via their Facebook page. Still no human on the other end of the line though.

Next time I saw the 12-week offer, I added a response in the comments + used tagging to make sure they got a notification:

"@[The Economist] Hello, I would like to try out your 12week offer but only for the 12 weeks. Is it possible to cancel after this 12 weeks? This is the third channel I use to get an answer to my question. Hopefully with success. Many thanks, Karel"

Because nobody is responding to my message, I decided to use a third channel and send out my first tweet to The Economist. No success.

After a few days, I started with responding to each message that The Economist page published. Each time I added the same reply:

"@[The Economist] Hello, I would like to try out your 12week offer but only for the 12 weeks. Is it possible to cancel after this 12 weeks? This is the third channel I use to get an answer to my question. Hopefully with success. Many thanks, Karel"

No response from Facebook. I tried again with a second, less polite, tweet and a second email.

tweet

And you might have guessed it … no answer. After a while I got a bit annoyed and used Facebook to express it…

By now I have send 2 e-mails, 2 tweets, 7 Facebook chat messages and commented on 4 posts of The Economist. Without receiving an answer from any of these 4 channels. And I’m still not taking benefit of the 12 week try-out offer of The Economist.

That’s why I dedicate this last blog and tweet to claim the ‘Award for Most Eager To-Be Subscriber of The Economist’. Chriss Stibbs or Zanny Minton Beddoes may invite me to London for the hand-out. I would be happy to share my customer experience in their omni-channel offer and (lack of) social media support.

Many thanks!

PS: also thanks to Arne for helping me see the humor in this situation 🙂

Tagged , , ,

Digitaal becomes human in de interimsector


Randstad Interim

Momenteel draait een reclamespot van Randstad op de radio. Je hoort er hoe ze eerst traditioneel zoeken naar een vacature:

  • Regio: x + 10km
  • Ervaring: y jaar
  • Sector: metal

Daarna pakt Randstad uit dat hun medewerkers het verschil maken doordat ze hun kandidaten écht kennen: “Oh, Y, dat is echt een toffe, zij houdt niet van landschapbureau’s en hare vrije dag op woensdag is heilig.”

Als ze het in de praktijk ook effectief toepassen, is dit een mooi voorbeeld van hoe we van het digitale terug naar het menselijke verschuiven.

Digitaal als stap voor op de concurrentie

Ook de interimsector is namelijk door een digitale revolutie gegaan. De jobs werden (worden nu nog steeds) in jobkranten geadverteerd en aan vitrines uit gehangen. Met de komst van de desktop PCs en het internet werd deze jobmarkt ook gedigitaliseerd. Zowel de werkgevers als de kandidaten konden nu van een zoekmotor op de website van het interimkantoor gebruik maken om naar jobs te zoeken. Wat later kon je je ook abonneren, zodat die jobs ook automatisch naar je kwamen. Om te zorgen dat de juiste jobs naar jou kwamen, kan je ook je profiel instellen.

Terwijl dit vroeger vernieuwend was (en voor de eerste interims misschien revolutionair), is het nu alledaags geworden. Normaal.

Het is te zeggen: als je zo geen gedigitaliseerde zoekmachine met eigen profiel en voorkeuren meer hebt, ben je gewoon niet meer mee! Het digitale is normaal geworden in de wereld van de jobmarkten.

Onderscheiden via de klantenrelatie

Wanneer het digitale nog vernieuwend is, kan je als bedrijf daarmee concurreren. Wanneer ondertussen iedere concurrent óók over zo’n gedigitaliseerde jobomgeving beschikt, is het niet meer vernieuwend. Het is de standaard geworden. Maar je moet je wel nog kunnen onderscheiden met de concurrentie. Hier is waar het humane, het menselijke, aspect weer belangrijk wordt.

De medewerkers van Randstand kennen niet alleen de tools, ze kennen de mensen die in de tools zitten, de kandidaten. De medewerkers hebben de tools ter beschikking, maar het is nog altijd een mens die de beslissing neemt en achter die tools zit.

Randstad is (voor mij) het eerste interimkantoor dat uitpakt met het digitale gecombineerd met het menselijk aspect.

Meer lezen

When Digital becomes human – Steven Van Belleghem

Tagged , , ,
%d bloggers like this: