Method and system for measuring user engagement using click/skip in content stream using a probability model
Method, system, and programs for measuring user engagement. In one example, a model generated based on user activities with respect to a plurality pieces of content is obtained. One or more actual occurrences of the user activities with respect to one piece of the plurality pieces of content are identified. One or more future occurrences of the user activities with respect to the piece of content are estimated based on the model. A user engagement score with respect to the piece of content is calculated based on the one or more actual occurrences of the user activities and the one or more future occurrences of the user activities.
1. A method implemented on at least one machine, each of which has at least one processor, storage, and a communication platform connected to a network for identifying content to recommend to a user, the method comprising the steps of:
displaying a content stream including a plurality of pieces of content on a device operated by the user;
obtaining by a processor, for each piece of content and an associated user operation of a plurality of user operations, a corresponding probability of occurrence of the user operation on the piece of content, the probability of occurrence being computed based on one or more parameters associated with the displaying and a speed and/or acceleration of scrolling the content stream;
detecting by the processor, for each displayed piece of content, an actual occurrence of at least one operation of the plurality of operations;
computing, for each piece of content, a first score associated with an amount of time the piece of content is displayed, the first score being computed based on a relative display position of the piece of content with respect to a reference piece of content;
calculating, for each piece of content, an engagement score based on the probability of occurrence of the at least one operation being performed on the piece of content, the actual occurrence of the at least one operation being detected, the first score, and a stream depth of the content stream;
assigning, for each piece of content, a rank based on the calculated engagement score of the piece of content; and
identifying the content to be recommended to the user, the content being identified based on the assigned rank of the each piece of content.
2. The method of claim 1 , wherein the user operation is one of clicking a piece of the plurality pieces of content, skipping one or more pieces of the plurality pieces of content, and abandoning at least some of the plurality pieces of content.
3. The method of claim 1 , wherein the one or more parameters associated with the displaying include at least one of
a display position of the piece of content, a presentation style of the piece of content, and a type of information included in the piece of content.
4. The method of claim 1 , wherein the identified content is recommended to the user in real time.
5. The method of claim 1 , wherein the first score is computed based on a type of device operated by the user.
6. A system for identifying content to recommend to a user, the system comprising:
at least one processor configured to:
display a content stream including a plurality of pieces of content on a device operated by the user;
obtain for each piece of content and an associated user operation of a plurality of user operations, a corresponding probability of occurrence of the user operation on the piece of content, the probability of occurrence being computed based on one or more parameters associated with the displaying and a speed and/or acceleration of scrolling the content stream;
detect, for each displayed piece of content, an actual occurrence of at least one operation of the plurality of operations;
compute, for each piece of content, a first score associated with an amount of time the piece of content is displayed, the first score being computed based on a relative display position of the piece of content with respect to a reference piece of content;
calculate, for each piece of content, an engagement score based on the probability of occurrence of the at least one operation being performed on the piece of content, the actual occurrence of the at least one operation being detected, the first score, and a stream depth of the content stream;
assign, for each piece of content, a rank based on the calculated engagement score of the piece of content; and
identify the content to be recommended to the user, the content being identified based on the assigned rank of the each piece of content.
7. The system of claim 6 , wherein the user operation is one of clicking a piece of the plurality pieces of content, skipping one or more pieces of the plurality pieces of content, and abandoning at least some of the plurality pieces of content.
8. The system of claim 6 , wherein the one or more parameters associated with the displaying include at least one of: a display position of the piece of content, a presentation style of the piece of content and a type of information included in the piece of content.
9. The system of claim 6 , wherein the identified content is recommended to the user in real time.
10. A non-transitory machine-readable medium having information recorded thereon for recommending content, wherein the information, when read by a machine, causes the machine to perform the following:
displaying a content stream including a plurality of pieces of content on a device operated by the user;
obtaining, for each piece of content and an associated user operation of a plurality of user operations, a corresponding probability of occurrence of the user operation on the piece of content, the probability of occurrence being computed based on one or more parameters associated with the displaying and a speed and/or acceleration of scrolling the content stream;
detecting, for each displayed piece of content, an actual occurrence of at least one operation of the plurality of operations;
computing, for each piece of content, a first score associated with an amount of time the piece of content is displayed, the first score being computed based on a relative display position of the piece of content with respect to a reference piece of content;
calculating, for each piece of content, an engagement score based on the probability of occurrence of the at least one operation being performed on the piece of content, the actual occurrence of the at least one operation being detected, the first score, and a stream depth of the content stream;
assigning, for each piece of content, a rank based on the calculated engagement score of the piece of content; and
identifying the content to be recommended to the user, the content being identified based on the assigned rank of the each piece of content.
11. The medium of claim 10 , wherein the user operation is one of clicking a piece of the plurality pieces of content, skipping one or more pieces of the plurality pieces of content, and abandoning at least some of the plurality pieces of content.
12. The medium of claim 10 , wherein the one or more parameters associated with the displaying include at least one of a display position of the piece of content, a presentation style of, piece of content, and a type of information included in the piece of content.