Unraveling the linguistic nature of specific autobiographical memories using a computerized classification algorithm

In the present study, we explored the linguistic nature of specific memories generated with the Autobiographical Memory Test (AMT) by developing a computerized classifier that distinguishes between specific and nonspecific memories. The AMT is regarded as one of the most important assessment tools to study memory dysfunctions (e.g., difficulty recalling the specific details of memories) in psychopathology. In Study 1, we utilized the Japanese corpus data of 12,400 cue-recalled memories tagged with observer-rated specificity. We extracted linguistic features of particular relevance to memory specificity, such as past tense, negation, and adverbial words and phrases pertaining to time and location. On the basis of these features, a support vector machine (SVM) was trained to classify the memories into specific and nonspecific categories, which achieved an area under the curve (AUC) of .92 in a performance test. In Study 2, the trained SVM was tested in terms of its robustness in classifying novel memories (n = 8,478) that were retrieved in response to cue words that were different from those used in Study 1. The SVM showed an AUC of .89 in classifying the new memories. In Study 3, we extended the binary SVM to a five-class classification of the AMT, which achieved 64%-65% classification accuracy, against the chance level (20%) in the performance tests. Our data suggest that memory specificity can be identified with a relatively small number of words, capturing the universal linguistic features of memory specificity across memories in diverse contents.