ResearchSpace

Using N-grams to identify mathematical topics in MXit lingo

Show simple item record

dc.contributor.author Butgereit, LL
dc.contributor.author Botha, RA
dc.date.accessioned 2012-04-23T15:34:13Z
dc.date.available 2012-04-23T15:34:13Z
dc.date.issued 2011-09
dc.identifier.citation Butgereit, LL and Botha, RA. Using N-grams to identify mathematical topics in MXit lingo. Annual Conference of the South African Institute of Computer Scientists and Information Technologists (SAICSIT 2011), Cape Town, South Africa, 3-5 October 2011, pp 40-48 en_US
dc.identifier.isbn 978-1-4503-0878-6
dc.identifier.uri http://dl.acm.org/citation.cfm?id=2072221.2072227&coll=DL&dl=ACM&CFID=76903344&CFTOKEN=61329174
dc.identifier.uri http://hdl.handle.net/10204/5814
dc.description Copyright: 2011 ACM. This is an ABSTRACT ONLY. en_US
dc.description.abstract N-grams are used to quantify the similarity between two documents or the similarity between two collections of words. This paper shows how N-grams of length 3 and 4 both coupled with text processing (including stop word removal and stemming according to MXit spelling conventions) can be used to categorize very short mathematical conversations conducted in MXit lingo into broad mathematical groups such as algebra, geometry, trigonometry, and calculus. MXit lingo is an abbreviated form of written English which children, teenagers and young adults utilise when communicating using the popular MXit chat mechanism over cell phones. Conversations from the "Dr Math" project were used for this analysis. "Dr Math" is a mathematical tutoring service which links primary and secondary school pupils to tutors from local universities. The tutors assist the pupils with their mathematics homework. en_US
dc.language.iso en en_US
dc.publisher ACM en_US
dc.relation.ispartofseries Workflow;7410
dc.subject MXit lingo en_US
dc.subject MXit spelling en_US
dc.subject N-grams en_US
dc.subject Dr Math en_US
dc.subject C³TO en_US
dc.title Using N-grams to identify mathematical topics in MXit lingo en_US
dc.type Conference Presentation en_US
dc.identifier.apacitation Butgereit, L., & Botha, R. (2011). Using N-grams to identify mathematical topics in MXit lingo. ACM. http://hdl.handle.net/10204/5814 en_ZA
dc.identifier.chicagocitation Butgereit, LL, and RA Botha. "Using N-grams to identify mathematical topics in MXit lingo." (2011): http://hdl.handle.net/10204/5814 en_ZA
dc.identifier.vancouvercitation Butgereit L, Botha R, Using N-grams to identify mathematical topics in MXit lingo; ACM; 2011. http://hdl.handle.net/10204/5814 . en_ZA
dc.identifier.ris TY - Conference Presentation AU - Butgereit, LL AU - Botha, RA AB - N-grams are used to quantify the similarity between two documents or the similarity between two collections of words. This paper shows how N-grams of length 3 and 4 both coupled with text processing (including stop word removal and stemming according to MXit spelling conventions) can be used to categorize very short mathematical conversations conducted in MXit lingo into broad mathematical groups such as algebra, geometry, trigonometry, and calculus. MXit lingo is an abbreviated form of written English which children, teenagers and young adults utilise when communicating using the popular MXit chat mechanism over cell phones. Conversations from the "Dr Math" project were used for this analysis. "Dr Math" is a mathematical tutoring service which links primary and secondary school pupils to tutors from local universities. The tutors assist the pupils with their mathematics homework. DA - 2011-09 DB - ResearchSpace DP - CSIR KW - MXit lingo KW - MXit spelling KW - N-grams KW - Dr Math KW - C³TO LK - https://researchspace.csir.co.za PY - 2011 SM - 978-1-4503-0878-6 T1 - Using N-grams to identify mathematical topics in MXit lingo TI - Using N-grams to identify mathematical topics in MXit lingo UR - http://hdl.handle.net/10204/5814 ER - en_ZA


Files in this item

Thumbnail
Name: Butgereit_2011_AB ...
Size: 41.52Kb
Format: PDF
View/Open

This item appears in the following Collection(s)

Show simple item record