Humanizing chatbots to improve the student experience
How conversational UI helps students communicate with chatbots
- Students want instant access to information, 24/7—chatbots can provide that service
- Designing the conversation involves creating a chatbot persona that represents the institution
- Good design creates a successful conversation between the chatbot and the end user (i.e. the student)
Chatbots and voice assistants are growing in popularity and users; Millennials and Gen Z now expect them to be available in almost all the platforms and devices they use. And Gartner predicts that 25 percent of customer service operations will use these two technologies, which are forms of conversational UI (user interface), by 2020.
So, what is conversational UI and why the popularity? Conversational UI allows users to converse with computers in the same way they would with a person. This ability to communicate in a natural way makes using technology more convenient and efficient, and higher education institutions stand to gain a lot out of leveraging the same.
Benefits of using conversational UI in higher education
Students want instant gratification and expect on-demand services. They expect that their higher education experience will mirror their consumer experience. Conversational UI can help institutions meet those expectations by offering benefits such as:
- A connected experience—Institutions often offer a number of services and resources, in addition to academics, through separate portals that students have to wade through and navigate in order to find what they’re looking for. This creates a broken experience that can be mended by using a chatbot or voice assistant that allows the student to quickly access the information without having to browse for it.
- Instant access to information, 24/7—Students want an instant response and sometimes seek information outside of operational hours. Chatbots can provide this service.
- Comfort—Students are sometimes hesitant to ask faculty, advisors, and administrators questions that they believe to be silly and are more open to directing such questions to a bot.
Utilizing this technology is also beneficial to faculty, staff, and advisors. Conversational UI can gather information about students’ needs and help these stakeholders better serve students by freeing their time to focus on questions or issues that cannot be resolved by a computer.
Conversational UI also supports institutions by helping to meet business goals around saving money, improving reach, and increasing student satisfaction and engagement.
Designing conversational UI
Designing a conversational UI involves two aspects: creating a bot persona and designing the conversation.
Creating a bot persona
When people engage in conversation, they make assumptions about the type of person they are speaking with. These assumptions come from characteristics like word choice and vocal attributes. Based on these characteristics, institutions can design the system persona to represent their brand.
Some of the factors that shape vocal attributes are:
- The institution’s image and brand—The bot’s persona needs to be representative of the institution’s thoughts, opinions, behaviors, and mission statement. Therefore, the speaking tone needs to consistent with the tone used on the institution’s website, social media, and other communication materials.
- The role of the system with respect to the user—Ensuring that the language clearly communicates how the bot is going to serve the user is essential for a positive user experience as it enables users to manage expectations.
- The end users: who they are, how frequently they will use the system, and what their expectations are—A full understanding of bot users must be gained in order for the bot personality to be similar to theirs. This helps end users feel greater trust and comfort in conversing with the bot.
- The content, context, or task types of the application—The material that the bot deals with and the circumstances involved influence the tone. For example, a bot that’s created to share details about campus events might have a more casual tone and approach as opposed to one that deals with students’ grades or degree progress.
Humans are wired to personify, and users will ascribe personality traits to the system persona. The best strategy is to determine the personality while designing, rather than leave it up to chance.
Designing the conversation
Good conversational design is not just about writing good prompts. It’s about setting user expectations and designing a conversation that goes beyond one turn. In order to create a successful conversation, each exchange between the system and the user needs to be seamless. A good conversational design will include a dialog strategy, error/recovery strategy, and grammar type.
The dialog strategy defines how the system will respond to requests made by the user. This may come in the form of a prompt, response, or even a call to a third-party application. Dialogs often require a number of prompts and responses to collect all the information needed to complete a request.
Having a good strategy for error handling is just as important as the dialog strategy. Users can forgive hearing “I’m sorry, I don’t know the answer to your question” once, maybe twice, but will easily become frustrated with each repetition. The goal of a good error strategy is to offer contextual assistance to help guide the user to a successful conclusion.
Grammar type is a list of words and/or phrases the system anticipates the user to say. Each user input is mapped to a response defined within the dialog strategy. In order to reduce errors, the grammar list is often very comprehensive. It is hard to predict all the variations a user might say, so defining which type of grammar to use is important for providing the greatest amount of recognition coverage. For example, if the user is attempting to understand the schedule for a particular course, the bot would request the course title. The user’s response could be Economics, Accounting, or any other course title, all of which exist within the grammar list.
Design decisions are influenced by user and business needs. For example, branding influences the creation of the persona. A comprehensive understanding of the users’ and business’ point of view ahead of time greatly reduces the risk of making poor design decisions. Creating an effective design requires an end-to-end thought process.
Conversational design principles are closely related to those of UX, or user experience design. A common process for designing a conversation might include the following methodologies:
- Identify business needs and branding requirements of the institution.
- Develop user and system personas. The user persona serves as a representation of a group of users that would use the chatbot. The system persona represents the institution.
- Craft user stories that determine how user needs and pain points relate to the business requirements.
- Write sample dialogs that demonstrate how a user will interact with a system and take into consideration dialog strategy, error recovery strategy, and grammar type.
- Write scripts for the chatbot to follow. The scripts are hi-fidelity conversational design that include the full end-to-end conversational experience, error handling, and user statements and responses.
- Test the design with users to understand performance and identify areas for improvement.
Looking to the future
Conversational UI is transforming the way users interact with technology and is on its way to becoming the preferred interface. More than 37 percent of businesses have implemented artificial intelligence technology this year. And the chatbot market in the U.S. is expected to exceed $1 billion by 2025. This technology—within the higher education space—only serves to further current offerings and provide students, faculty, and staff with a more connected and elevated experience.