Are We There Yet? A Systematic Literature Review on Chatbots in Education

This means you can answer questions or start collecting the information your human agents need to address customer queries faster. While this may be expected in an emerging research area, future research will benefit from a greater degree of coherence and cohesiveness in the field. For the broader chatbot uses and user groups, the rich literature needs to be continuously updated, especially when it comes to user motivations and behaviour of emerging user groups.

The more functionality you inject into the user experience, the more likely users will engage with your bot. One important limitation to be mentioned here is the exclusion of alternative keywords for our search queries, as we exclusively used chatbot as keyword in order to avoid search results that do not fit our research questions. A second limitation may lie in the formation of categories and coding processes applied, which, due to the novelty of the findings, could not be built upon theoretical frameworks or already existing code books. Although we have focused on ensuring that codes used contribute to a strong understanding, the determination of the abstraction level might have affected the level of detail of the resulting data representation.

Top 10 Challenges to Chatbot Development – An In-depth look

This includes knowledge on specific demographics, for example, vulnerable users, such as children, elderly and users with special needs, as well as user groups within particular application areas. Moreover, research still needs to assess whether there are systematic differences in the adoption and usage of chatbots driven by socio-demographic characteristics. While there is a rapidly expanding body of knowledge relevant to chatbot research, rooted in long-standing research fields, current research and knowledge are fragmented across disciplines, application areas, and communities. However, we are now at a point in time where it is beneficial to stake out common directions for future research. Its chatbot-only service is free, though it also offers teletherapy services with a human for a fee ranging from $15 to $30 a week; that fee is sometimes covered by insurance. Making chatbots a part of your customer service strategy increases agent efficiency, reduces contact center costs, and improves customer satisfaction.

• However, there is still a wide variety of terms in use in reference to the object of this converging research interest.
• Based on such an analysis and comparison, a generalization of the research across application areas seems possible.
• Machine Learning is the system’s ability to learn from past experiences without human involvement and use what they have learned.
• It is important to hire a designer or a human factors designer to help with the conversations with your chatbot.

Usually, people don’t like to spend a long time on the phone before they can talk with a human agent. After the first, second, and third filters, we identified 505 candidate publications. We continued our filtering process by reading the candidate publications’ full texts resulting in 74 publications that were used for our review.

SEO In 2024: Top Priorities, Challenges, And Opportunities

Although global and national health bodies highlight the importance of mental health in a pandemic, COVID-19 mental health needs have reportedly been under-addressed24. Front-line clinicians are often not trained in emergency psychological support, and mental health practitioners are in short supply24. Short-term, chatbots may mitigate the psychological harm of isolation, even though they cannot maintain human-level conversations. Simply disclosing concerns and receiving emotionally supportive responses can have positive value in some contexts25. If effectively designed and deployed, chatbots may lessen the long-term harm of pandemic-related isolation, trauma, and depression13,26. Preliminary evidence shows that chatbots may reduce mental health symptoms, but long-term outcomes are unclear and worthy of future investigation6,27.

Being able to address these challenges head on in the beginning will allow businesses to succeeded past these challenges of implementing their first chatbot. At the C-Suite level, I’ve often found that it takes a long time for them to understand the value behind a chatbot. The conversation always seems to be around “how do we use a chatbot to reduce headcount or money”, when the actual real value is in the DATA that a chatbot can provide.

Challenge 8: Limited responses

In this paper, we propose a research agenda which has been distilled through a series of dedicated workshops on chatbot research—CONVERSATIONS—with intensive discussions among researchers and practitioners actively working on chatbots. Furthermore, this collaborative approach enables us to gain chatbot challenges insights from different perspectives to address opportunities, challenges, and perceived research needs within the field. The research agenda serves as a concise research roadmap, offering links to pertinent studies for those readers who are interested in delving further into specific fields.

Also, there are times when what a user is trying to explain, but a chatbot is unable to understand, resulting in high dissatisfaction. Hence, businesses need to improve technology occasionally and keep their chatbot solutions updated. Businesses may also hire a dedicated development team to develop customized chatbot solutions per their business requirements.

Conversational AI

For instance, if a customer seeks information about a particular product or service, a chatbot may provide a generic response that does not address the customer’s concerns. Moreover, customers may lose trust in the brand and switch to a competitor offering a more personalized experience. A chatbot is AI powered software that can chat with a user, just like humans, via messaging applications, websites, mobile apps, or telephone. This conversational AI can answer questions, perform actions, and make recommendations according to the user’s needs. Chatbots, if effectively designed and deployed, could help us by sharing up-to-date information quickly, encouraging desired health impacting behaviors, and lessening the psychological damage caused by fear and isolation. Despite this potential, the risk of amplifying misinformation and the lack of prior effectiveness research is cause for concern.

At the forefront for digital customer experience, Engati helps you reimagine the customer journey through engagement-first solutions, spanning automation and live chat. This will hep provide the initial utterances and intents that you need to develop for your chatbot. The other option is that you can create your own custom chatbot, but that will also be expensive because you will need an engineer to custom code your chatbot and also maintain it. Having a team to support it when things go wrong is also something to consider as well.

What are the top chatbot use cases in healthcare?

For businesses with heavy call flow, chatbots provide another mode of communication to alleviate high call volume. So, let’s break down different ways to use chatbots so you can learn how to incorporate them to better support your brand and alleviate some tasks off your employee’s plates. Since 36% of consumers think that chatbot’s accuracy could make efforts to improve, it’s essential to figure out where to incorporate chatbots and where human interaction is still necessary. Over the last couple of years, more companies have been integrating chatbots into their communications process to engage with customers.

Even though Chatbot development challenges can be cost-cutting in their operation and labor,  it could be costly as it requires a high level of coding. If you are developing an internal chatbot, you’ll often feel resistance because chatbots have a preconceived notion of being able to takeaway jobs. Being able to message to employees that the goal is to help reduce redundant work in order to allow employees to focus on higher level work will make them more productive and doing the work they want to be doing. When we met with our financial team to get agreement on the financial value statements for our internal chatbot, implementing this chatbot was determined that there was more of an experiential gain and user efficiency into finding the information. In my experience, the technical currency that we had to manage included how often we had to upgrade the framework, which was not even the platform, it was just the version of the platform. After delivering over a dozen skills, having to go back to working on old skills felt like it took us a few steps back at a time when we were just making progress on increasing adoption due to how fast we were releasing new skills.

Five vectors of progress in conversational AI

When you are ready to invest in conversational AI, you can identify the top vendors using our data-rich vendor list on voice AI or chatbot platforms. Chatbots can extract patient information by asking simple questions such as their name, address, symptoms, current doctor, and insurance details. The chatbots then, through EDI, store this information in the medical facility database to facilitate patient admission, symptom tracking, doctor-patient communication, and medical record keeping. Not only will chatbots help with customer interactions on brand’s websites, but there will be more use within brand’s apps, with 50% of the chatbot usage through apps. Businesses can also use social media chatbots for updates and send mass messages. Keep your customers informed with daily or weekly announcements about deals, events, and promotions.

And even AI’s proponents argue computers aren’t ready, and may never be ready, to replace human therapists — especially for handling people in crisis. “In order to address this huge mental health crisis we have in our nation — and even globally — I think digital treatments and AI can play a role in that, and at least fill some of that gap in the shortage of providers and resources that people have,” Cheng says. Maybe the most controversial applications of AI in the therapy realm are the chatbots that interact directly with patients like Chukurah Ali. Technology has gotten good at identifying and labeling emotions fairly accurately, based on motion and facial expressions, a person’s online activity, phrasing and vocal tone, says Rosalind Picard, director of MIT’s Affective Computing Research Group.

• An example for Mentoring chatbots supporting Life Skill is the Logo counseling chatbot, which promotes healthy self-esteem (Engel et al., 2020).
• The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice.
• For the topic of chatbots in education, a value between these two numbers can be assumed, which is why an approach of integrating several publisher-independent databases was employed here.
• Chatbots may be integrated into collaborative processes forming what Grudin and Jacques [45] refer to as humbots, that is, human-chatbot teams which handle challenging service queries better than chatbots alone and more efficiently than humans alone.

It can give your users tips or show them new features and link out to videos or pages where they can find more information. And if issues become more complex, chatbots can gather all the relevant information your staff needs to solve the problem first thing the next day. This accelerates resolution time and gives your customers the confidence to know that things are heading in the right direction. If you have a small support team, it might sound daunting to expand your presence to other channels. However, chatbots can take conversations from start to finish, meaning you don’t necessarily need more head count. Future research should be directed at addressing the identified key research challenges.

Deloitte Insights and our research centers deliver proprietary research designed to help organizations turn their aspirations into action. Our analysis of patents in the area of conversational AI reveals that this might be possible soon. Deloitte Insights and our research centers deliver proprietary research designed to help organizations turn their aspirations into action. A not-for-profit organization, IEEE is the world’s largest technical professional organization dedicated to advancing technology for the benefit of humanity.© Copyright 2024 IEEE – All rights reserved. Alison Callahan, Kristin Sainani, and Elias Aboujaoude for their valuable feedback.