Anomia (i.e., impaired word retrieval) is one of the most common and debilitating deficits experienced by stroke survivors with aphasia, an acquired disorder characterized by impaired language. Although many anomia treatments exist, treatment response is modest and inconsistent across studies, and the extent of generalization to everyday contexts-the therapy gold standard-is largely unknown. The critical gap between actual outcomes and the therapeutic potential of naming therapy is tied to problems with current treatment delivery practices (i.e., low/unknown dosage, massed practice delivery, and decontextualized training). In this research, we aim to demonstrate that a novel smartwatch-based ecological momentary intervention (EMI) that delivers high-dosage semantic feature training throughout daily life has the potential for overcoming these issues. Every day for six weeks, 20 PWA will complete 24 trials of semantic feature EMI distributed over the day (from 10am-8pm) and delivered by a smartwatch. The EMI trial flow will include five steps: 1) a prompt alert and audiovisual "Ready to name a picture?" cue, 2) a first naming attempt after a YES response, 3) the repetition of an auditory model, 4) semantic feature verification via yes/no questions, and 5) a second naming attempt. To contextualize training further, trained items will be clustered into location categories (e.g., home, pharmacy), and we will use the mobile device's location detection to match PWA's location and item category for ~50% of trials. In Aim #1, we will establish preliminary efficacy of this EMI by determining the extent to which semantic feature EMI improves naming of trained items and generalizes to untrained, related contexts. We predict that the EMI will significantly improve 1) naming of trained items and semantically related, untrained items relative to semantically unrelated items and 2) subjective and objective measures of functional communication effectiveness. Given the novelty of our EMI, the second two aims will focus on identifying key factors of semantic feature EMI user experience (Aim #2) and trends between therapy response and the treatment delivery factors of dosage, trial spacing, and item-location congruence (Aim #3). The proposed research is innovative because of the novel use of EMI for aphasia, our combined application of distributed practice and context-dependent training, and the future promise of extending our system to other types of evidence-based treatment and to other clinical populations, as well as to in-situ "just-in-time" interventions that can intervene in real time during the moment of communication breakdown. The significance of this research lies in its ability to provide technology that automatically tracks dosage metrics; its potential for increasing knowledge regarding which therapy delivery factors impact outcomes; and its promise for providing PWA alternative paths to receive therapy. Successful completion of this research will lead to an R01 application aimed at establishing the efficacy of this novel therapy compared to gold-standard, clinician-provided treatment and determining which active treatment ingredients contribute to outcomes.