Carrick, C.; Watters, C.: Automatic association of news items (1997)
0.00
0.002930285 = product of:
0.04102399 = sum of:
0.04102399 = weight(_text_:media in 1549) [ClassicSimilarity], result of:
0.04102399 = score(doc=1549,freq=2.0), product of:
0.13212246 = queryWeight, product of:
4.6838713 = idf(docFreq=1110, maxDocs=44218)
0.02820796 = queryNorm
0.31049973 = fieldWeight in 1549, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
4.6838713 = idf(docFreq=1110, maxDocs=44218)
0.046875 = fieldNorm(doc=1549)
0.071428575 = coord(1/14)
- Abstract
- Examines the problem of the association of related times of different media type, specifically photos and stories involved in the automatic generation of electronic editions. Determines to what degree any 2 news items refer to the same news event. This metric can be used: to link multimedia items that can be shown together, such as a video, photo, and text story related to a shipwreck or state visit; and to form clusters of very similar items from a variety of sources so that 1 or 2 can be chosen to represent that event in an edition. Discusses the specific assocoation of text and photo news items, although the approach applies to a larger domain of news including scripted news video clips and sripted radio broadcasts