Here I will occasionally put up helpers/explainers/aids related to queries people have had on the #corpusmooc .
For example there were a number of questions about collocation statistics so I knocked up a chart based on a video and one of the readings – Identifying Collocations [https://magic.piktochart.com/output/16856740-identify_collocations]
I did some similar charts for previous corpusmoocs you can look up in the corpusmooc section.
Another set of queries was about distinguishing collocations from colligations (see previous corpusmooc for a related chart), this time round found a nice example from John Sinclair:
For example, the English letter string second can be claimed to have two primary meanings based on results of a collocation analysis: (i) ‘next to the first’ when it is used together with words such as the, world, war, year, child and wife, and (ii) ‘a unit of time’ when it is preceded by words such as per, radians and cycles. In addition to being attracted to different lexical contexts, the two primary meanings of second also prefer different grammatical contexts: second as ‘next to the first’ is often a part of a definite noun phrase, while second as ‘a unit of time’ can be usually found in an indefinite noun phrase (Sinclair 1991: 107). Hence, the collocational preferences of the two senses correlate with the colligational preferences.
which was cited in the following pdf – [http://pubman.mpdl.mpg.de/pubman/item/escidoc:2304786:2/component/escidoc:2304785/Collocation%20and%20colligation.pdf]
Hope these are of use : )