The expanding horizons of corpus analysis Brian MacWhinney Carnegie Mellon University Abstract By including a focus on multimedia interactions linked to transcripts, corpus linguistics can vastly expand its horizons. This expansion will rely on two continuing developments. First, we need to develop easily used methods for each of the ten analytic methods we have examined, including lexical analyses, QDA (qualitative data analysis), automatic tagging, language profiles, group comparisons, change scores, error analysis, feedback studies, conversation analysis, and modeling. Second, we need to work together to construct a unified database for language studies and related sciences. This database must be grounded on the principles of open access, data-sharing, interoperability, and integrated structure. It must provide powerful tools for searching, multilinguality, and multimedia analysis. If we can build this infrastructure, we will be able to explore more deeply the key questions underlying the structure and functioning of language, as it emerges from the intermeshing of processes operative on eight major timeframes. 1. Introduction Corpus linguistics has benefitted greatly from continuing advances in computer and Internet hardware and software. These advances have made it possible to develop facilities such as BNCweb (bncweb.lancs.ac.uk), LDC (Linguistic Data Consortium) online, the American National Corpus (americannationalcorpus. org), TalkBank (talkbank.org), and CHILDES (childes.psy.cmu.edu). In earlier periods, these corpora were limited to written and transcribed materials. However, most newer corpora now include transcripts linked to either audio or video recordings. The development of this newer corpus methodology is facilitated by technology which makes it easy to produce high-quality video recordings of face-to-face interactions. Also, we now have common access to software that can link transcripts to the media at the level of the utterance and sometimes the word. These linked transcripts can then be accessed over the web, either through downloading or through browser plug-ins. Among the various available resources, the collections at TalkBank and CHILDES are unique in providing users with completely open, online access to a large quantity of audio or video that has been linked to transcripts on the level of individual utterances. Using these links, researchers can play back thousands of different conservational interactions and study in detail their interactional and linguistic features. These materials can then be subjected to the analytic methods of corpus-based linguistics. By applying both the traditional methods of corpus