Processing a content item with regard to an event and a location
The invention described herein can be implemented in numerous ways, including as a process; an apparatus; a system; a composition of matter; a computer program; a product embodied on a computer readable storage medium, e.g., RAM, ROM, and other hardware storage devices; and/or a processor, such as a processor configured to execute instructions stored on and/or provided by a memory coupled to the processor. In this specification, these implementations, or any other form that the invention may take, may be referred to as techniques. In general, the order of the steps of disclosed processes may be altered within the scope of the invention. Unless stated otherwise, a component such as a processor or a memory described as being configured to perform a task may be implemented as a general component that is temporarily configured to perform the task at a given time or a specific component that is manufactured to perform the task. As used herein, the term ‘processor’ refers to one or more devices, circuits, and/or processing cores configured to process data, such as computer program instructions.
1. A method for associating a content item with an event, comprising:
receiving a content item;
determining a location associated with the received content item using a processor;
comparing the received content item with an existing event, wherein the existing event comprises a previously processed content item and a previously associated location, wherein comparing the received content item with the existing event comprises:
determining a weighted overlap between the determined location and the previously associated location of the existing event;
determining an indicia of relatedness between the received content item and the existing event, wherein the indicia of relatedness is not based on location;
wherein the indicia of relatedness includes a time overlap between a time associated with the received content item and a time associated with the existing event;
wherein the time overlap comprises being within a 24 hour window; and
associating the received content item with the existing event based on the comparison, wherein the comparison also includes a threshold level of indicia of relatedness between the received content item and the existing event, and wherein the threshold level of indicia of relatedness required for the content item to be determined to be associated with the existing event increases as a degree of the weighted overlap between the determined location and the location previously associated with the existing event decreases.
2. The method as in claim 1 , wherein the indicia of relatedness comprises a bi-gram overlap.
3. The method as in claim 2 , wherein the bi-gram overlap comprises a frequency based overlap between bi-grams associated with the received content item and bi-grams associated with a content item associated with the existing event.
4. The method as in claim 1 , wherein the indicia of relatedness comprises a unigram similarity.
5. The method as in claim 4 , wherein the unigram similarity comprises a similarity between unigrams associated with the received content item and unigrams associated with a content item associated with the existing event.
6. The method as in claim 1 , wherein the indicia of relatedness comprises an entity overlap.
7. The method as in claim 6 , wherein an entity overlap comprises a frequency based overlap between named entities associated with the received content item and named entities associated with a content item associated with the existing event.
8. The method as in claim 1 , wherein the existing event is one of a plurality of candidate events determined at least in part using one or more prior received content items.
9. The method as in claim 8 , wherein the plurality of candidate events are each assigned a rating based on weightings of indicia of similarity between the content item and the one or more prior received content items associated with each of the plurality of candidate event as well as a number of the one or more prior received content items associated with a given candidate event.
10. A system for associating a content item with an event, comprising: a processor configured to:
receive a content item;
determine a location associated with the received content item;
compare the received content item with an existing event, wherein the existing event comprises a previously processed content item and a previously associated location, wherein comparing the received content item with the existing event comprises:
determining a weighted overlap between the determined location and the previously associated location of the existing event;
determining an indicia of relatedness between the received content item and the existing event, wherein the indicia of relatedness is not based on location;
wherein the indicia of relatedness includes a time overlap between a time associated with the received content item and a time associated with the existing event;
wherein the time overlap comprises being within a 24 hour window; and
associate the received content item with the existing event based on the comparison, wherein the comparison also includes a threshold level of indicia of relatedness between the received content item and the existing event, and wherein the threshold level of indicia of relatedness required for the content item to be determined to be associated with the existing event increases as a degree of the weighted overlap between the determined location and the location previously associated with the existing event decreases; and
a memory coupled to the processor and configured to provide the processor with instructions.
11. The system as in claim 10 , wherein the indicia of relatedness comprises a bi-gram overlap.
12. The system as in claim 11 , wherein the bi-gram overlap comprises a frequency based overlap between bi-grams associated with the received content item and bi-grams associated with a content item associated with the existing event.
13. The system as in claim 10 , wherein the indicia of relatedness comprises a unigram similarity.
14. The system as in claim 13 , wherein the unigram similarity comprises a similarity between unigrams associated with the received content item and unigrams associated with a content item associated with the existing event.
15. The system as in claim 10 , wherein the indicia of relatedness comprises an entity overlap.
16. The system as in claim 15 , wherein an entity overlap comprises a frequency based overlap between named entities associated with the received content item and named entities associated with a content item associated with the existing event.
17. The system as in claim 10 , wherein the existing event is one of a plurality of candidate events determined at least in part using one or more prior received content items.
18. The system as in claim 17 , wherein the plurality of candidate events are each assigned a rating based on weightings of indicia of similarity between the content item and the one or more prior received content items associated with each of the plurality of candidate event as well as a number of the one or more prior received content items associated with a given candidate event.
19. A computer program product for associating a content item with an event, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:
receiving a content item;
determining a location associated with the received content item;
comparing the received content item with an existing event, wherein the existing event comprises a previously processed content item and a previously associated location, wherein comparing the received content item with the existing event comprises:
determining a weighted overlap between the determined location and the previously associated location of the existing event;
determining an indicia of relatedness between the received content item and the existing event, wherein the indicia of relatedness is not based on location;
wherein the indicia of relatedness includes a time overlap between a time associated with the received content item and a time associated with the existing event;
wherein the time overlap comprises being within a 24 hour window; and
associating the received content item with the existing event based on the comparison, wherein the comparison also includes a threshold level of indicia of relatedness between the received content item and the existing event, and wherein the threshold level of indicia of relatedness required for the content item to be determined to be associated with the existing event increases as a degree of the weighted overlap between the determined location and the location previously associated with the existing event decreases.