Determining quality of a summary of multimedia content

A quality metric of a summary of a multimedia content item is determined based, in part, on semantic similarities of the summary and content item using at least two of a first content metric quantifying a similarity 204 between the text portions of the summary and multimedia content; a second content metric quantifying a similarity 212 between the image portion of the summary and multimedia content; and a third content metric quantifying a similarity, or coherence, 208 between the text and image portion of the summary. This may use vector analysis; the vectors of the summary and the vectors of the multimedia content item are compared 220, 228 to determine semantic similarity.