Systems and methods for the analysis of user experience testing with AI acceleration
Systems and methods for AI assisted analysis of a user experience study are provided. A study objective (a goal of the study) and data relating to all possible navigation routes within a digital interface are received. Simulated clickstreams for navigating from any state of the digital interface to the study objective are generated. This simulated clickstream data is then used to train one or more machine learning models to determine a most efficient path to achieve the study objective from any state of the digital interface. Subsequently, study results from many different participants is received. Key events are then identified within the study results. Additionally, the likelihood of failure for each of the plurality of study results is predicted using the machine learning model, and information density of the plurality of study results is determined.
1. A method for artificial intelligence (AI) assisted analysis of a user experience study comprising:
training an AI model to detect incidents of interest, wherein the incidents of interest include user abandonment, user failure, user frustration, and delayed completion of an objective using a first training set; identifying the incidents of interest within a second training set;
training the AI model to detect at least one trigger for the identified incidents of interest using the second training set;
receiving at least one study for analysis; identifying the incidents of interest within the at least one study;
receiving a query for a specific incident of interest within the study;
selecting the trigger for the specific incident of interest using the AI model; and generating at least one analytics output including the selected trigger;
wherein the analytics output includes at least one of a heat map, a clickstream, a sentiment analysis, an audio clip, a video clip, a question chart with confidence intervals, and a word cloud.
2. The method of claim 1 , wherein the query is a natural language question.
3. The method of claim 1 , wherein the second training set includes feedback from a human if the insights provided are helpful and relevant.
4. The method of claim 1 , wherein the first raining set includes study results here a human annotates incidents of interest.
5. The method of claim 1 , further comprising getting feedback on the generated analytics output.
6. The method of claim 5 , further comprising generating additional analytics output responsive to the feedback.
7. The method of claim 1 , wherein the analytics output includes at least one of a heat map, a clickstream, a sentiment analysis, an audio clip, a video clip, a transcript, a data point or key performance indicator (KPI), screenshot, a data table with counts, percentages, averages, medians and standard deviations, question chart with or without confidence intervals, an open ended answer, keywords, a dendrogram, a treemap, cross tabulation or comparison data table, dashboard, emotions chart and a word cloud.