Treat Humans Humanely and They Might Just Like IVR!
January 07, 2008
Interactive Voice Response (IVR) telephony systems have developed a notorious, and often deserved, reputation for being frustrating -- and even infuriating -- to use. Currently deployed IVRs are generally perceived by users as obstacles installed by companies to keep callers from reaching expensive human agents, rather than helpful tools that can effectively serve caller needs.
The glaring disconnect between what companies aim to achieve in deploying IVR systems (better customer service) and what they actually do achieve (customer frustration) can be squarely laid on the shoulders of shabby Voice User Interface (VUI) design and implementation. The vast majority of IVRs deployed today are, simply put, shamefully unusable, and customers calling into call centers detest them.
The viscerally strong emotional reaction that callers have against IVRs is fully justified. IVRs not only fail to do their job, but they fail while pushing on some of our most sensitive emotional buttons. They treat us disrespectfully, with little intelligence and thoughtfulness, and exhibit an unsettling degree of irrationality that breeds contempt, if not revulsion against them.
A system that treats users with respect is more likely to win the cooperation of its users than one that does not. Here are some instances of how the system should behave respectfully towards the user:
Respect the user's time: for instance, avoid having the user suffer through long prompts; telling the user how long they need to wait for an agent; offering to the user the option to be called back; letting the user interrupt when they hear their options.
Respect the user's freedom: for instance, letting them zero out if they don't want to interact with the IVR; letting get back to the IVR while they are waiting.
Don't lie to the user: for example, don't tell them that you are going to route them to an agent and then have them interact with the IVR some more.
Don't blame the user: in cases where an error occurs, the system should always take the blame.
Never hang up on the user: the act of ending a conversation unilaterally is the ultimate act of disrespect in the context of a dialog. Always make sure that the decision to end the dialog is consensual.
Tell the user what you are going to do: for instance, the system should always tell the user that it needs to pause the dialog interaction for a few seconds to execute a back end action (e.g., retrieve something from the database); if the system should always tell the user that it is transferring the user to an agent.
Don't switch modalities on the user without telling them: if the system needs to remove speech recognition from the user, then it must tell them that it is removing it and must offer an explanation why.
On the flip side, the best way to win a user's respect and therefore their cooperation is by acting intelligently. Here are some examples:
Know the user's preferences: if the caller has selected English in previous interactions, don't keep asking them what language they wish to use every time they call. Note the language preference, remember it, and default to it.
Know the user's level of expertise: treat frequent users who know the system differently from first time or infrequent users.
Anticipate the user's requests: if a user has recently placed an order, chances are that they are calling to inquire about that order. Offer the caller the status of that order next time they call.
Detect and act on request spikes: if the system is experiencing a sudden spike in calls, have the VUI adapt its behavior in light of that spike: for instance, if every month the first three weekdays experience a spike in people calling to inquire about their checking balance, then during the first three days of the month, have the system volunteer to offer the user's balance before lapsing to the main menu.
Nothing unnerves a user more than an irrational machine. Every instance of inconsistency by the system will occasion the user to ask, "Why is the system behaving like this? Did I miss something or is the system just badly designed?" Obviously, such questioning can only hurt the user's confidence in the system's ability to help them solve their problem.
In Language: be consistent in how you refer to objects, properties and actions across prompts and menus. Don't use "ticket" in one prompt and "case" in another; "incorrect" in one and "invalid" in another; "log in" in one and "sign on" in another.
In Voice: avoid mixing DTMF with recordings; and avoid using more than one voice in your VUI.
In modality: if the user can speak their answer in one menu, don't take that ability away from them in another menu, unless you explain to them why you are taking it away from them.
Across menus: if you let the user request "repeat" in one menu, don't take that ability away from them in another menu.
Across contexts: if users are responding to an infomercial and the infomercial tells the viewers that by calling the line they will get to a sales agent, then make sure that the IVR does not offer options that have nothing to do with sales: e.g., offering them to be connected to the help desk or to billing.
IVRs don't need to be the bane of call center callers if designed with the above three basic principles in mind. Have the IVR treat the caller with respect, give the system the intelligence and information it needs to treat each caller as an individual with specific needs, and ensure that the system's behavior is consistent, rational, and predictable. Do that and you will see the abiding hatred callers seemingly have for your IVR evaporate.
Dr. Ahmed Bouzid heads the Partnerships program at Angel.com and has over 15 years of experience in the Speech and Natural Language Processing industry. He has written widely on Voice User Interface design and Natural Language Processing. He is the author of the VUI post blog at http://www.thevuipost.com
Don't forget to check out TMCnet’s White Paper Library, which provides a selection of in-depth information on relevant topics affecting the IP Communications industry. The library offers white papers, case studies and other documents which are free to registered users.