Automated Classification of Cognitive Decline and Probable Alzheimer's Dementia Across Multiple Speech and Language Domains.

BACKGROUND: Decline in language has emerged as a new potential biomarker for the early detection of Alzheimer's disease (AD). It remains unclear how sensitive language measures are across different tasks, language domains, and languages, and to what extent changes can be reliably detected in early stages such as subjective cognitive decline (SCD) and mild cognitive impairment (MCI). METHOD: Using a scene construction task for speech elicitation in a new Spanish/Catalan speaking cohort (N = 119), we automatically extracted features across seven domains, three acoustic (spectral, cepstral, and voice quality), one prosodic, and three from text (morpholexical, semantic, and syntactic). They were forwarded to a random forest classifier to evaluate the discriminability of participants with probable AD dementia, amnestic and nonamnestic MCI, SCD, and cognitively healthy controls. Repeated-measures analyses of variance and paired-samples Wilcoxon signed-ranks test were used to assess whether and how performance differs significantly across groups and linguistic domains. RESULTS: The performance scores of the machine learning classifier were generally satisfactorily high, with the highest scores over .9. Model performance was significantly different for linguistic domains (p < .001), and speech versus text (p = .043), with speech features outperforming textual features, and voice quality performing best. High diagnostic classification accuracies were seen even within both cognitively healthy (controls vs. SCD) and MCI (amnestic and nonamnestic) groups. CONCLUSION: Speech-based machine learning is powerful in detecting cognitive decline and probable AD dementia across a range of different feature domains, though important differences exist between these domains as well. SUPPLEMENTAL MATERIAL: https://doi.org/10.23641/asha.23699733.

A classification of user-generated content into consumer decision journey stages.

In the last decades, the availability of digital user-generated documents from social media has dramatically increased. This massive growth of user-generated content has also affected traditional shopping behaviour. Customers have embraced new communication channels such as microblogs and social networks that enable them not only just to talk with friends and acquaintances about their shopping experience, but also to search for opinions expressed by complete strangers as part of their decision making processes. Uncovering how customers feel about specific products or brands and detecting purchase habits and preferences has traditionally been a costly and highly time-consuming task which involved the use of methods such as focus groups and surveys. However, the new scenario calls for a deep assessment of current market research techniques in order to better interpret and profit from this ever-growing stream of attitudinal data. With this purpose, we present a novel analysis and classification of user-generated content in terms of it belonging to one of the four stages of the Consumer Decision Journey Court et al. (2009) (i.e. the purchase process from the moment when a customer is aware of the existence of the product to the moment when he or she buys, experiences and talks about it). Using a corpus of short texts written in English and Spanish and extracted from different social media, we identify a set of linguistic patterns for each purchase stage that will be then used in a rule-based classifier. Additionally, we use machine learning algorithms to automatically identify business indicators such as the Marketing Mix elements McCarthy and Brogowicz (1981). The classification of the purchase stages achieves an average precision of 74%. The proposed classification of texts depending on the Marketing Mix elements expressed achieved an average precision of 75% for all the elements analysed.