The computerized scoring algorithm for the autobiographical memory test: updates and extensions for analyzing memories of English-speaking adults

Abstract

The Autobiographical Memory Test (AMT) has been central in psychopathological studies of memory dysfunctions, as reduced memory specificity or overgeneralised autobiographical memory has been recognised as a hallmark vulnerability for depression. In the AMT, participants are asked to generate specific memories in response to emotional cue words, and their responses are scored by human experts. Because the manual coding takes some time, particularly when analysing a large dataset, recent studies have proposed computerised scoring algorithms. These algorithms have been shown to reliably discriminate between specific and non-specific memories of English-speaking children and Dutch- and Japanese-speaking adults. The key limitation is that the algorithm is not developed for English-speaking adult memories, which may cover a wider range of vocabulary that the existing algorithm for English-speaking child memories cannot process correctly. In the present study, we trained a new support vector machine to score memories of English-speaking adults. In a performance test (predicting memory specificity against human expert coding), the adult-memory algorithm outperformed the child-memory variant. In another independent performance test, the adult-memory algorithm showed robust performances to score memories that were generated in response to a different set of cues. These results suggest that the adult-memory algorithm reliably scores memory specificity.

Computerised memory specificity training (c-MeST) for the treatment of major depression: a study protocol for a randomised controlled trial

“…In each session, participants will be asked to provide a memory of an event that occurred yesterday and on that day. Participants will be provided with automated feedback as to whether the response is specific or not via the application of an algorithm developed to classify written autobiographical memories 18. Where responses are not specific, participants will be asked to reattempt, and will be given feedback to add episodic detail to the response (eg, when, where, and with whom the experience occurred), and ensure it is discussed as past tense and is specific in nature rather than an extended experience that lasts more than a day, or a category of events.…”

“…Consistent with face-to-face MeST, participants provide written responses to cue words over a series of sessions. They receive feedback as to whether AMs are specific or not according to a computerised algorithm which is trained to distinguish these differences using machine learning 18 19. Given that c-MeST has been shown to improve memory specificity, the next step is to test this adaptation in a clinical sample to assess whether it can also produce reductions in depressive symptoms.…”

A study protocol for a randomised trial of adjunct computerised memory specificity training (c-MeST) for major depression in youth: targeting cognitive mechanisms to enhance usual care outcomes in mental health settings

“…Participants will also be asked to provide one memory of an event that occurred on that day. Participants will be provided with automated feedback as to whether the response is specific or not via the application of an algorithm developed to classify written autobiographical memories [33]. If the answer is specific, they will be prompted to add spatial-temporal, sensoryperceptual and other contextual details to their responses.…”

Development of a Structured Interview to Explore Interpersonal Schema of Elderly Living Alone Based on Autobiographical Memory

“…Many researchers have developed several types of interview and performance evaluation tools to assess autobiographical memories [24][25]. However, most of the measurements have been developed for the purpose of identifying disease-specific impairment of autobiographical memory, with limited validity for evaluation of the extent and degree of impairment such as the accuracy and specificity of memory, and impossible to evaluate core beliefs or relationship schema quantitatively [24,[26][27].…”