Credibility enhancement for online comments and recommendations

A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:

• monitor activity relating to an object in an online network;
• maintain, on at least one storage device, historical data indicative of one or more prior user interactions with the object based on the activity monitored;
• determine a baseline of activity for the object based on the activity monitored;
• in response to detecting a user interaction by a first user with the object, record information relating to the user interaction, wherein the information recorded includes at least one of the following:
• length of time of the user interaction, degree of user engagement with the object during the user interaction, amount of the object the user interaction involved, and degree of user usage of the object during the user interaction;
• and
• in response to detecting a submission of a user recommendation from the first user for the object:
• perform an analysis of the information recorded in view of the historical data;
• and
• based on the analysis, determine a credibility score for the user recommendation, wherein the credibility score represents a degree of confidence in reliability of the first user to recommend the object;
• wherein, the object comprises readable content or a video, the program instructions are further executable by the processor to cause the processor to:
• determine a likelihood that the first user completed reading or viewing the object;
• and
• send an astroturfing warning to one of the first user or an administrator of the online network in response to determining the likelihood is below a pre-determined threshold;
• wherein, the object comprises readable content, the program instructions are further executable by the processor to cause the processor to:
• record reading speed, reading progress, and textual content indicative of words, language, or items read by the first user during the user interaction;
• correlate words included in the readable content against the textual content recorded to determine whether the user recommendation is credible;
• and
• prompt the first user to re-read the readable content in response to determining the user recommendation is not credible;
• and
• wherein presentation and prominence of user recommendations for objects displayed on an electronic device is controlled based on credibility scores to decrease impact of astroturfing, crowdturfing, and spamming on the presentation.