A Survey of the Perceived Text Adaptation Needs of Adults with Autism

Proceedings of Recent Advances in Natural Language Processing, pages 1356–1363, Varna, Bulgaria, Sep 2–4, 2019. https://doi.org/10.26615/978-954-452-056-4_155 1356 A Survey of the Perceived Text Adaptation Needs of Adults with Autism Victoria Yaneva, Constantin Or˘asan, Le An Ha and Natalia Ponomareva Research Institute in Information and Language Processing, University of Wolverhampton, UK {v.yaneva, c.orasan, ha.l.a, n.ponomareva}@wlv.ac.uk Abstract NLP approaches to automatic text adaptation often rely on user-need guidelines which are generic and do not account for the differences between various types of target groups. One such group are adults with high-functioning autism, who are usually able to read long sentences and comprehend difficult words but whose comprehension may be impeded by other linguistic constructions. This is especially challenging for real-world user- generated texts such as product reviews, which cannot be controlled editorially and are thus in a stronger need of automatic adaptation. To address this problem, we present a mixed- methods survey conducted with 24 adult web- users diagnosed with autism and an age- matched control group of 33 neurotypical par- ticipants. The aim of the survey is to iden- tify whether the group with autism experi- ences any barriers when reading online re- views, what these potential barriers are, and what NLP methods would be best suited to im- prove the accessibility of online reviews for people with autism. The group with autism consistently reported significantly greater dif- ficulties with understanding online product re- views compared to the control group and iden- tified issues related to text length, poor topic organisation, identifying the intention of the author, trustworthiness, and the use of irony, sarcasm and exaggeration. 1 Introduction The aim of automatic text adaptation (also known as automatic text simplification) is to make the meaning of texts more accessible to specific target groups such as language learners or people with cognitive disabilities. To achieve this, the develop- ment of automatic systems is driven by guidelines that describe the needs of the target group, but very often these guidelines are generic. For exam- ple, one of the most authoritative sources of such guidelines for people with cognitive disabilities, the European Guidelines for the Production of Easy-to-Read Information (Freyhoff et al., 1998), lists requirements that fit the profile of people with moderate to severe comprehension deficits, but not those of more highly able individuals. As a result, the majority of text simplification strategies aim to reduce sentence and word complexity, while ap- proaches to other aspects of text adaptation (e.g. clarifying the opinion of the author or strengthen- ing the text organization) receive less attention. In this paper we address this issue by providing insight into the needs of a specific subgroup, peo- ple with high-functioning autism, who are known to be able to read and comprehend complex texts, but may struggle with specific aspects of their comprehension. For example, readers with high- functioning autism are usually able to cope with the meaning of complex words but are known to struggle with non-literal language or with com- bining the meaning of individual text …

Content truncated to 500 words