|
| EPSRC Reference: |
GR/S15419/01 |
| Title: |
Facilitating language play in non-speaking children through computer-supported joke construction |
| Principal Investigator: |
Dr A Waller |
| Other Investigators: |
|
| Researcher Co-investigator: |
|
| Project Partner: |
| Speech and Language Therapy (Dundee) |
Tayside University Hospital Trust |
|
|
| Department: |
School of Computing |
| Organisation: |
University of Dundee |
| Scheme: |
Standard Research |
| Starts: |
01 October 2003 |
Ends: |
31 March 2007 |
Value (£): |
181,218
|
| EPSRC Research Topic Classifications: |
| Human-Computer Interactions |
|
|
| EPSRC Industrial Sector Classifications: |
| Creative Industries |
Information Technologies |
| Education |
|
|
| Related Grants: |
|
| Panel History: |
| Panel Date | Panel Name | Outcome |
|
05 Nov 2002
|
People & Interactivity Panel (Technology) - Nov 02
|
Deferred
|
|
|
Summary |
|
There is evidence that language play, including using puns and other jokes, has a beneficial effect on a child's developing language and communication skills. Children with communication impairments are often reliant on augmented communication aids in order to carry on conversations, but these aids give little scope for generating novel language. This inhibits experimentation with language and limits the trying out of humorous ideas, which can in turn have a stultifying effect on the child's language development. We propose to address this deficiency in the language environment of the non-speaking child, by providing a software tool which promotes humorous language play. Starting from our previous work on the automated generation of punning riddles, we will design and implement a program which allows the user to experiment with the construction of simple jokes. The user interface of this system will be specially designed to be accessible to children with communication and physical disabilities. We will then test the efficacy of the system by observing and evaluating the use that our target population of children make of the software.
|
| Final Report Summary |
Children with disabilities such as cerebral palsy often have severe physical and speech impairments which affect their communication with other people. Such children usually rely on electronic speech generating devices where pre-stored words and phrases are accessed using simplified keyboards. Consequently, they may struggle to acquire functional literacy and their range of conversational interactions may be limited. In particular, banter, joking and word-play are impossible for most children with complex communication needs (CCN). Such restrictions have an adverse effect not just on language development but on social skills. To tackle this, we have constructed software which allows children with CCN to play with words, making up novel riddles (puns) of their own and having the computer tell the newly built riddles to their friends. A colourful and intuitive interface, especially designed to accommodate physical and cognitive disabilities, allows the children to generate novel jokes, such as:
What kind of tree is nauseated?
A sick-amore.
What do you call a spicy missile?
A hot shot.
We hope that exploration of facets of language (similarity of sound, ambiguity of meaning, etc.) will improve a child's skills and increase the motivation to communicate and interact.
The joke-building part of the software was based on PhD research at Edinburgh University in the 1990s, but considerable software engineering was needed to make the ideas usable for the children. A major task was creating a vast dictionary of words and phrases containing (along with basic relationships between words) ratings for how alike words sounded (for making puns), and estimates for each word-meaning of how familiar it might be to a young child. Also crucial was the construction of a bright, colourful, user-friendly graphical display appropriate for children. The user-interface can easily be adjusted in many different ways (using a simple control panel) to suit an individual user. One option is to have pictorial symbols displayed with words in the jokes, to assist children with limited literacy. Another set of options makes the computer use synthetic speech to "read out" messages, labels, and (most importantly) jokes.
Designing the software involved consultation with teachers, speech therapists and adult users of aided communication, and early versions of the program were tested by appropriate users. After several versions of the program, with continual revision and improvement, we tested the usability and effectiveness of the software by taking it into primary schools to get feedback from children. At Capability Scotland's Corseford Primary School, nine pupils (all with cerebral palsy) were introduced to the program, and explored its possibilities in a number of sessions spread over eight weeks. The overall outcome was very positive: the children picked up how to use the software very quickly, loved using it, often took the initiative in trying out the capabilities of the program, and showed great pleasure in telling (or having the computer "tell") their jokes to friends and family. Teachers and parents were very enthusiastic about the effect that the sessions had on the children in terms of increased self-confidence and motivation to communicate.
This project set out with two central goals: to establish whether such a system could indeed be constructed, and if so, whether it could be used by children with CCN. Both these questions have been answered positively.
There could be various further developments: using the software for other communication purposes (e.g. second language learning), or with other populations (e.g. children with autism, adults with learning disabilities); widening the types of jokes (and the types of linguistic knowledge) used; examining the long-term effects of children using such software; using the software to test ideas about what kinds of jokes work best.
|
| Further Information: |
|
| Organisation Website: |
http://www.dundee.ac.uk |
|
|