<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Ben Sheehan on Medium]]></title>
        <description><![CDATA[Stories by Ben Sheehan on Medium]]></description>
        <link>https://medium.com/@bensheehan?source=rss-b5d67ecf69f------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/0*TsjZ1mqH1KYtuiJ1.</url>
            <title>Stories by Ben Sheehan on Medium</title>
            <link>https://medium.com/@bensheehan?source=rss-b5d67ecf69f------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Tue, 17 Nov 2026 20:27:30 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@bensheehan/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[A proven method to increase charity donations.]]></title>
            <link>https://medium.com/@bensheehan/a-proven-method-to-increase-charity-donations-24422497ef73?source=rss-b5d67ecf69f------2</link>
            <guid isPermaLink="false">https://medium.com/p/24422497ef73</guid>
            <category><![CDATA[charity]]></category>
            <category><![CDATA[research-reports]]></category>
            <category><![CDATA[donations]]></category>
            <category><![CDATA[charitable-giving]]></category>
            <dc:creator><![CDATA[Ben Sheehan]]></dc:creator>
            <pubDate>Wed, 09 Feb 2022 05:35:32 GMT</pubDate>
            <atom:updated>2022-02-09T05:35:32.903Z</atom:updated>
            <content:encoded><![CDATA[<h3>Charitable organizations are facing serious challenges. Money is tight and COVID hurt consumers. Meanwhile, there are more and more charities competing for every dollar. Recent research from the Journal of Advertising, provides details of an evidence-based, simple solution to increase the amount of time and money people are willing to donate to charity.</h3><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*3xN54XBPNj66vsHHfE6IXQ.jpeg" /></figure><blockquote><a href="https://www.tandfonline.com/doi/full/10.1080/00913367.2021.1887012">Jin, H., Kim, H., Suh, J., Sheehan, B., &amp; Meeds, R., (2021). Ego depletion and charitable support: The moderating role of self-benefit and other-benefit charitable appeals, Journal of Advertising 50(4): 479–493.</a></blockquote><p>Charities can use a range of different messages and appeal strategies. The question is which types of messages work for which people, at which times? Understanding this, can increase overall donations. And make the world a better place :)</p><p>Consider two different charitable appeals. The first one explains that donating money will really help someone else. This is considered an “other benefit message”. Your donation benefits someone else. The second appeal explains that donating money can be a tax write-off for you. This is considered a “self-benefit message”. Your donation directly benefits you.</p><p>Imagine someone is asking you to donate your time. Explaining that your time will help build shelter for homeless people is an other-benefit message (homeless people benefit). Explaining that you will be gaining experience, while connecting with like-minded professionals is a self-benefit message (you benefit).</p><p>The researcher presents three experiments which demonstrate that people prefer an other-benefit message when they are not ego-depleted. But prefer a self-benefit message when they are ego-depleted.</p><p>So what is ego-depletion? Ego-depletion occurs when people use up all of their available will power. So making tough choices, exercising self-control, dealing with the stress of a typical workday — all of these things can result in ego-depletion. Charities can change their message appeals based on their understanding of ego-depletion.</p><p><strong>Tell me how to increase charity donations</strong></p><p>The researchers suggest two concrete, easy-to-enact recommendations.</p><ol><li>First, ego-depletion occurs naturally over the course of the day. Therefore — charities could use an other-benefit message in the morning (“Help the poor. Donate now”) and use a self-benefit message in the evening (“Reduce your tax bill. Donate now”). This is easily done with online advertising.</li><li>Second, charities could also change their donation message based on their target audience’s job. This is because some peoples’ jobs require a lot of self-control and those people are more likely to suffer from ego-depletion. For example, customer service people, executives, medical professionals etc. are more likely to be ego-depleted, and therefore, may prefer a self-benefit message.</li></ol><p>In conclusion, generosity among depleted people appears to be self-seeking — but we won’t hold that against them…</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*AwL6D3hrGPbsMcTuXK7iCg.jpeg" /></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=24422497ef73" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Experiment Results: “Opposites attract” or “Birds of a feather flock together”]]></title>
            <link>https://medium.com/chat-bots/experiment-results-opposites-attract-or-birds-of-a-feather-flock-together-897b27dbd091?source=rss-b5d67ecf69f------2</link>
            <guid isPermaLink="false">https://medium.com/p/897b27dbd091</guid>
            <category><![CDATA[social-robotics]]></category>
            <category><![CDATA[bots]]></category>
            <category><![CDATA[research-summary]]></category>
            <category><![CDATA[bot-personality]]></category>
            <category><![CDATA[user-testing]]></category>
            <dc:creator><![CDATA[Ben Sheehan]]></dc:creator>
            <pubDate>Mon, 18 Sep 2017 21:30:53 GMT</pubDate>
            <atom:updated>2017-09-18T21:30:53.403Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*zbsohFLTE_heNzB_9lPphQ.jpeg" /></figure><p>Welcome to part 2 of my Nerd Out series, where I take some interesting scholarly research from human-computer interaction &amp; psychology and present them in a simple summary — with notes on how to apply the findings to your chatbot. <a href="https://chatbotsmagazine.com/rethinking-politeness-in-chatbots-interesting-research-findings-6c3a91871e5f">First part here</a>.</p><h3><strong>Basic Question:</strong></h3><p>You have probably heard the proverb that opposites attract. Well that may work for magnets. Others say that birds of a feather flock together. So, which is it — similarities or differences and how can your bot leverage this idea for fun and profit?</p><p>We are talking ‘personality’ for your chatbot. Others have written about this before (<a href="https://chatbotsmagazine.com/designing-a-chatbots-personality-52dcf1f4df7d">1</a>,<a href="https://chatbotsmagazine.com/responsive-personality-design-in-chatbots-a96b1c2373ba">2</a>,<a href="https://chatbotsmagazine.com/4-reasons-why-bots-need-a-personality-not-a-vending-machine-brain-d1d4489fcf1a">3</a>). <strong>This is my academic spin on it</strong>. Understand that there are many different ways to measure personality. Here are just some of the validated instruments and tests that psychologists use –</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*1WuYWyrRD_Elg54J7KgYdA.png" /></figure><p><strong>But you are trying to build a bot here — not get your PhD</strong>. So, I would recommend you use “The Big Five” model. You can remember it’s parts through the acronym O.C.E.A.N as per the image below. Today we are looking at extroversion / introversion and its conceptual relative — dominance / submission.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/800/1*04qClnB3st--bmvEbqMQqw.png" /></figure><h3><strong>Basic Answer:</strong></h3><p>Similarity attraction works. “Birds of a feather stick together” is the angle you want to adopt. Did you know that people with similar personalities are more likely to be happy in their marriage (Berscheid &amp; Walster 1969; Byrne 1971)? It seems pretty obvious, but hey — this is what us nerds like us want to prove.</p><p><strong>Now to prove it to you</strong>. I have 2 nice experiments to share. Similarity attraction is the theory to use, because it has been applied to human-computer interaction.</p><p><strong>EXPERIMENT ONE:</strong></p><blockquote>Moon, Y &amp; Nass, C. 1996. How real are computer personalities? Psychological responses to personality types in human-computer interaction. Communication Research, 23(6). Pg. 651–674.</blockquote><p>The researchers took a bunch of students from Stanford University and measured their personality to determine if they were ‘dominant’ or ‘submissive’. Then they divided them into 2 groups based on their scores. The researchers took a computer program, more of a game really, where the human uses the computer to help them plan surviving alone in the desert. The user can only carry so much weight, so they have to prioritize what tools to take with them and what to leave behind. The computer is their partner in this decision-making exercise.</p><p>But there are actually 2 versions of the computer program — a dominant one and a submissive one:</p><ul><li>The dominant program makes statements like this “the compass <strong>should</strong> be lower in ranking. <strong>You can determine</strong> directions by observing shadow movements over a period of time”. And it rates is confidence in this statement as <strong>8/10</strong>.</li><li>The submissive program instead says “<strong><em>maybe</em></strong> the compass should be lower in ranking. <strong>You can <em>probably</em> determine</strong> directions by observing shadow movements over a period of time” and rates its confidence as <strong>3 / 10</strong>.</li></ul><p>I have highlighted the differences. So you have 4 groups, 4 pairings of human and machine as per image:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*znL9Vv5148f3oP_JQbHAIg.png" /></figure><p>And just as similarity attraction theory predicts, the 2 groups where the human personality matched the machines personality, users rated the machine higher for its (i) social attraction, (ii) intellectual attraction, (iii) utility and (iv) emotional satisfaction. All things you want to maximize in your own chatbot right?</p><p><strong>EXPERIMENT 2:</strong></p><blockquote>Nass, C &amp; Lee, K. 2001. Does computer synthesized speech manifest personality? Experimental tests of recognition, similarity-attraction and consistency attraction. Journal of Experimental Psychology: Applied, 7(3). Pg. 171–181.</blockquote><p><strong><em>Here is a similar experiment, but with a few important changes</em></strong>:</p><p>1./ Tested <strong>actual vocal cues</strong> instead of text. Important for anyone wanting to implement voice at some point e.g. Siri &amp; Cortana or a GPS etc.</p><p>2./ Instead of selecting equipment for desert survival, this experiment asked users to listen to a book review and decide if they wanted to buy that book. This is excellent for bot builders —<strong> testing a commercial outcome</strong>. I assume most readers are at least partially motivated by financial gain.</p><p>3./ Tested introverts versus extroverts. These variables are conceptually similar to dominance and submission, but different enough to be important and worth testing.</p><p>Here is a summary of the conditions, findings and how the extrovert / introvert variables were sensationalized using vocal cues.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*UjS9GDo_2bCDJVe5-6OLXg.png" /></figure><h3><strong>Why does similarity attraction work?</strong></h3><p>There are dominant theoretical mechanisms (read: explanations) which are kind of related.</p><p>1./ Byrnes Reinforcement Model (Byrne 1971): Reality is subjective. As such, we like ‘similar’ personalities because they reinforce the logic and consistency of our own internal model of the world. When we interact with people who are like us and agree with us, it validates our beliefs — and this feels good. <strong>TLDR; “This person functions in a logical manner”.</strong></p><p>2./ Information Processing Model (Ajzen 1974): We form opinions of people based on the information and cues we have available. This includes information we receive before we even meet them. This theory pus more weight on attitudes. We believe our attitudes are correct, so when we hear someone else has similar attitudes, we draw an inference from that to make predictions about other positive personality traits. <strong>TLDR; “I like recycling. They like recycling. Therefore, they are environmentally conscious, just like I am”.</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*ptXu53rTZOOPMedQ7q2U5A.png" /></figure><h3><strong>So what? Recommendations:</strong></h3><p>1./ <strong>Don’t just test your bots — test your users!</strong> You can get a bunch of valid and proven instruments to measure personality types online. Collect data on your users and build a profile of the average personality. Then you can adjust your bot to suit. **Just make sure you are using a good instrument from an academic journal — DO NOT use some Facebook trash. Email me if you want help finding the right tool.</p><p>2./ <strong>Read about the big 5 dimensions and start brainstorming.</strong> I only covered 1 dimension here. Where do your users sit regarding openness (curious versus consistent)? High openness scorers will appreciate an arty style, more emotional content, unusual ideas, something that stimulates their sense of curiosity. But openness could be perceived as a lack of focus to the low openness (consistent) user. These people want a facts and data driven interaction. This may seem too hard right now, but:</p><blockquote><strong>Imagine a future where this personality data is made available to you from Facebook as soon as your user connects. Your bot could adjust its personality on the spot! You be naive to think people are not working on this right now.</strong></blockquote><p>3./ <strong>Think of personality as more than just the bots name or avatar!</strong> Personality will inform the way it answers questions, the firmness of its recommendations, the pauses it takes between responses, the length of its responses — and even more if you plan on adding voice capabilities.</p><p>4./ <strong>Understand the mediating role of ‘trust’.</strong> Ok, just one more piece of theory. This is the latest on the subject. Singh, Tay &amp; Sankaran 2017 tested the model — but actually found that trust mediated the relationship. 2 people could agree about everything, but if A distrusts B — forget about it.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/570/1*YEJG0zWBCIeJUqwvWbb4Bw.png" /><figcaption>(Singh, R., Tay, Y &amp; Sankaran, K. 2017. Causal role of trust in interpersonal attraction from attitude similarity. Journal of Social and Personal Relationships, 34(5), pg. 717–731)</figcaption></figure><p>Thank you for reading. I really try to keep my writing grounded in evidence! If this article helped in any way, please hit the clap button below. I will be posting summaries and findings of chatbot related research here, so see you again soon. <a href="https://www.linkedin.com/in/ben-sheehan-mba-7507414/">Let’s connect on LinkedIn</a>!</p><iframe src="https://cdn.embedly.com/widgets/media.html?src=https%3A%2F%2Fupscri.be%2F58521e%3Fas_embed%3Dtrue&amp;dntp=1&amp;url=https%3A%2F%2Fupscri.be%2F58521e%2F&amp;key=a19fcc184b9711e1b4764040d3dc5c07&amp;type=text%2Fhtml&amp;schema=upscri" width="800" height="400" frameborder="0" scrolling="no"><a href="https://medium.com/media/c90883b0516ddbe5c59960c12a04bc64/href">https://medium.com/media/c90883b0516ddbe5c59960c12a04bc64/href</a></iframe><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=897b27dbd091" width="1" height="1" alt=""><hr><p><a href="https://medium.com/chat-bots/experiment-results-opposites-attract-or-birds-of-a-feather-flock-together-897b27dbd091">Experiment Results: “Opposites attract” or “Birds of a feather flock together”</a> was originally published in <a href="https://medium.com/chat-bots">Chatbots Magazine</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Rethinking Politeness in Chatbots: Interesting Research Findings]]></title>
            <link>https://medium.com/chat-bots/rethinking-politeness-in-chatbots-interesting-research-findings-6c3a91871e5f?source=rss-b5d67ecf69f------2</link>
            <guid isPermaLink="false">https://medium.com/p/6c3a91871e5f</guid>
            <category><![CDATA[conversational-ui]]></category>
            <category><![CDATA[chatbots]]></category>
            <category><![CDATA[naturallanguageprocessing]]></category>
            <category><![CDATA[bots]]></category>
            <category><![CDATA[voice-assistant]]></category>
            <dc:creator><![CDATA[Ben Sheehan]]></dc:creator>
            <pubDate>Mon, 11 Sep 2017 20:54:13 GMT</pubDate>
            <atom:updated>2022-02-09T07:08:29.484Z</atom:updated>
            <content:encoded><![CDATA[<p>Your chatbot should be polite to users. That is a no-brainer. No one wants to communicate with an impolite person, so why should a non-human entity be any different? This is especially the case with bots designed to replicate a customer service experience. <strong>But, did you know that users will also display politeness to your bot? Yes — it goes both ways.</strong></p><p>Humans will (on average) behave in a polite fashion in their interactions with a computer. This article will look at why this occurs and the evidence we have to support this claim, while providing some practical ideas you may want to implement.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/729/1*XEZ_I0PtuqGOIhoLKMGb1w.jpeg" /><figcaption>(Credit: Nomura, T of Ryukoku University, Japan. NOTE: What is polite is a cultural phenomenon)</figcaption></figure><p>Politeness is defined as the practical application of good manners and etiquette. Note, it includes much more than saying ‘please’ and ‘thank you’. Politeness also contains concepts like ‘socially desirable behaviours’. For example, lying is generally considered rude or undesirable, but if your wife asks you how dinner tastes — well, lying may be polite. So politeness provides a social function — a relationship glue — to keep everything working as it should. Humans are polite to other humans.</p><p>But humans are also polite to computers! WHAT THE… This is one of the main findings from a body of research called CASA or ‘Computers as Social Actors’. CASA is one of the coolest theories from human-computer interaction and if you are building chatbots, you need to understand it. In summary, CASA states that humans will subconsciously take the same mental models they use in human to human interaction and apply them in their dealings with computers.</p><p>This can result in some weird behavior from your users. In future articles, I will cover things like (i) gender stereotyping of bots and (ii) reciprocity. But let’s examine why CASA says that users will act politely towards computers.</p><h3>How Do We Know This?</h3><p>In 1999, some researchers from Stanford University’s Communications Department conducted an experiment. The looked at politeness in human to human interviews and appraisals. We know that humans give ‘socially desirable’ responses to each other. Well they wanted to see if this phenomenon held true in human-computer interaction. Here is a summary of the experiment and the findings.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*v1jO_jZ6VnrURFZvKlTNKA.png" /><figcaption>(Findings from: Nass, C., Moon, Y &amp; Carney, P. 1999. Are people polite to computers? Responses to Computer Based Interviewing Systems. Journal of Applied Social Psychology, 29(5). Pg. 1093–1110)</figcaption></figure><p>This is fascinating to me. Surely people know that a computer is an inanimate object. Users can’t hurt its feelings — because it doesn’t have any. What is going on here? In short -&gt; humans use ‘heuristics’ which are like mental shortcuts in decision making. Think rule of thumb, guestimates or educated guesses. We run scripts in our heads to make sense of the word. The computer talks to us like a person, so perhaps I could hurt its feelings like a person.</p><p>But Ben, maybe:</p><p>- The participants in the experiments were inexperienced computer users. They didn’t know the correct way to behave. NOPE. These were college students with extensive computer experience. And even if that was the case, chatbots are also very new and most consumers haven’t yet figured out the correct way to behave.</p><p>- OK, maybe the users were not responding to the computer, but actually responding to the human programmer who built the computer. Maybe they didn’t want to offend the programmer. NOPE. Later experiments on something called ‘Source Credibility’ discounted that explanation.</p><p>The participants treated the computer as an independent social actor. And chatbot users will probably be doing the same. Recommendations below…</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*54_Ele7-8lEHevn05rVmiA.png" /></figure><h3>So What? Design Implications:</h3><p>This has some interesting practical applications for those of us designing bots:</p><p>1./ <strong>Don’t get your bot to ask for an evaluation:</strong> If you want to know how your bot performs, run a focus group and collect feedback in person. Or provide a link to a third-party survey website and collect the user feedback there. If you have the money and time AB split testing is probably best. If user have to provide negative feedback about a bot directly to that bot, they are probably ‘greasing the wheels’ and being polite!</p><p>2./ <strong>UNLESS you want to pump up your results</strong>: Maybe you have to show some positive results to your client or your boss. Well now you know how 😊 Obviously, as a researcher, I cannot condone this lapse in methodological rigour, but hey — we all have bills to pay.</p><p>Start thinking about politeness in broader terms. Scripting your bot to say please and thank you is great, but that is just the ‘ticket to ride’ — the bare minimum you need. But hopefully this article inspires you.</p><p>Thank you for reading. I really try to keep my writing grounded in evidence! If this article helped in any way, please hit the clap button below. I will be posting summaries and findings of chatbot related research here, so see you again soon. Let’s connect on <a href="https://www.linkedin.com/in/ben-sheehan-7507414/">LinkedIn</a>!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=6c3a91871e5f" width="1" height="1" alt=""><hr><p><a href="https://medium.com/chat-bots/rethinking-politeness-in-chatbots-interesting-research-findings-6c3a91871e5f">Rethinking Politeness in Chatbots: Interesting Research Findings</a> was originally published in <a href="https://medium.com/chat-bots">Chatbots Magazine</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Realness in chatbot conversations: 4 things you have to get right.]]></title>
            <link>https://medium.com/chatbot-news-daily/realness-in-chatbot-conversations-4-things-you-have-to-get-right-3ace6be8c511?source=rss-b5d67ecf69f------2</link>
            <guid isPermaLink="false">https://medium.com/p/3ace6be8c511</guid>
            <category><![CDATA[messaging]]></category>
            <category><![CDATA[bots]]></category>
            <category><![CDATA[chatbots]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[natural-language]]></category>
            <dc:creator><![CDATA[Ben Sheehan]]></dc:creator>
            <pubDate>Fri, 08 Sep 2017 00:05:52 GMT</pubDate>
            <atom:updated>2017-09-13T12:03:28.004Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*6NFhG1SMQ_ipn5FNGn99Zg.png" /></figure><h3><strong>Basic Question:</strong></h3><p>What makes a conversation with a chatbot seem real? How can you script an authentic dialogue for your bot that will maintain engagement? I want to preface this article by saying that ‘realness’ may not be an appropriate goal for all bots. If your bot is very transactional, a streamlined way to get from A to Z should be the goal. However, if you are building something with a bit of personality, something designed to up-sell, foster a relationship or provide advice to your users — you have to think about realness. Let me put it another way. Is your chatbot (a) a new user interface e.g. just a new way to present the information from your website OR (b) a new staff member e.g. an intelligent actor designed to illicit information and help solve problems? If you are aiming to develop (b) -&gt; then realness can add to satisfaction and engagement. So what elements constitute ‘realness’ in an artificial conversational entity and where is the data to support these claims?</p><h3><strong>Basic Answer:</strong></h3><p>Morrissey, K. &amp; Kirakowski, J. 2013. Realness in chatbots: Establishing quantifiable criteria. Lecture Notes in Computer Science: Subseries — Artificial Intelligence and Bioinformatics, 4. Pg. 87–96.</p><h4>Four basic themes emerge which could inform your dialogue choices (specific language used) and the flow of the interaction.</h4><h3><strong>1. A chatbot should be conscientious:</strong></h3><p>Being a good conversational partner is tough as a human! It requires careful listening so that you can keep track of what was previously discussed and correctly interpret the subtly of meaning. You probably don’t enjoy talking to a person who jumps around too much in conversation, switching topics and answering questions with questions. Think about what information you want to collect on each user and clever ways to weave that back into the conversation. An obvious example is the user’s name. If the bot asks for it, make sure the bot also uses it later in the conversation. Scripting for context can be tough, but you can use the ‘entities’ function in api.ai or the ‘attributes’ function in chatfuel to help.</p><h3>2. A chatbot should display originality:</h3><p>Originality and authenticity go hand in hand. Not all humans are alike and the subtle differences between us help to form bonds. Perhaps you want to add a bit of personality to your bot? Nothing dramatic. Can your bot converse on a range of topics? A mix of ‘task focused’ messages and broad ‘small talk’ will add to realness. Originality can also relate to the flow. Many chatbot interactions feel like interviews! The questions only flow in 1 direction. Can your bot suggest a new topic of conversation? Can it subtly guide a user down a particular path in the dialogue — hopefully ending somewhere profitable for you.</p><h3>3. A chatbot should display manners:</h3><p>Maybe this goes without saying. But think about politeness. It means more than ‘please and thank you’. Manners can include apologies. Manners can include follow up a week after the previous conversation. Manners can include congratulating someone on the achievement of their goals. In human-human communications, manners include conversational repair and checking for clarity -&gt; aka paraphrasing. How can your chatbot show a user that it really is listening and interested?</p><h3>4. A chatbot should be thorough:</h3><p>This is about consistency. Does your chatbot use technical language in some responses, but revert back to slang or a casual tone further on in the interaction? Some of your users may be interacting with a chatbot for the first time! Maintaining a consistent approach to language and tone should help to keep a user at ease and form an appropriate mental model of what the bot is and what it can do.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*XPpiYIy50fjS2TWOotXShA.png" /></figure><h3>How Do We Know This:</h3><p>The authors of the paper cited above are from the School of Applied Psychology at University College in Cork, Ireland. They had users interact with conversational chatbots (not basic UI reimagining’s). The users then reviewed the chat logs with the researchers, identifying the things they thought the bot did well and where it fell short. These themes were then turned into statements and a second set of users evaluated ‘good bots’ (competition winners) and ‘bad bots’ (competition losers) against those statements to double check they had identified the right themes.</p><p>Think about what your chatbot is designed to do. Is it designed to ‘replicate’ something? If it replicating the ‘reserve a table’ function of a restaurant website, then keep it simple. But chatbots these days can dispense basic legal advice, offer a shoulder to cry on or help to motivate users in achieving their fitness goals. Realness matters.</p><p>Thank you for reading. If this article helped in any way, please hit the clap button below. I will be posting summaries and findings of chatbot related research here, so see you again soon. <a href="https://www.linkedin.com/in/ben-sheehan-mba-7507414/">Let’s connect on LinkedIn</a>!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=3ace6be8c511" width="1" height="1" alt=""><hr><p><a href="https://medium.com/chatbot-news-daily/realness-in-chatbot-conversations-4-things-you-have-to-get-right-3ace6be8c511">Realness in chatbot conversations: 4 things you have to get right.</a> was originally published in <a href="https://medium.com/chatbot-news-daily">Chatbot News Daily</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>