Method and apparatus for prediction of community reaction to a post

#Field of the Invention

#Embodiments of the present invention generally relate to online social communities and, more particularly, to a method and apparatus for predicting community reaction to a post to an online social community.

#Description of the Related Art

#FIG. 1 depicts a block diagram of a system for predicting community reaction to a post, according to one or more embodiments of the invention;

#FIG. 2 depicts a method for predicting community reaction to a post, as performed by the prediction engine of FIG. 1, according to one or more embodiments of the invention;

#FIG. 3 depicts a method for preparing data that is used to build a prediction model as performed by the text processor of FIG. 1, according to one or more embodiments of the invention;

#While the method and apparatus are described herein by way of example for several embodiments and illustrative drawings, those skilled in the art will recognize that the method and apparatus for predicting community reaction to a post to an online social community are not limited to the embodiments or drawings described. It should be understood, that the drawings and detailed description thereto are not intended to limit embodiments to the particular form disclosed. Rather, the intention is to cover all modifications, equivalents and alternatives falling within the spirit and scope of the method and apparatus for prediction of community reaction to a post to an online social community as defined by the appended claims. Any headings used herein are for organizational purposes only and are not meant to limit the scope of the description or the claims. As used herein, the word “may” is used in a permissive sense (i.e., meaning having the potential to), rather than the mandatory sense (i.e., meaning must). Similarly, the words “include”, “including”, and “includes” mean including, but not limited to. The term “online social community” means one or more groups of individuals who share a common interest and are connected by online interactions, such as posts to an Internet-based forum, newsgroup, enterprise marketer, blog, etc. Additionally, in some embodiments, the word “post” may include not only an initial message posted to a social community, but also a response message to an initial message or a response message.

#Embodiments of the present invention comprise a method and apparatus for predicting community reaction to a post to an online social community. The predictability of reactions on an online social community is quite stable with respect to time. That is, the way a community reacts to a particular way of expressing a particular idea does not change frequently. Thus, reactions to future posts can be predicted with reasonable confidence by learning from previous reactions to posts to an online social community. A prediction model is built for an online Internet community. A separate prediction model is built for each community of interest. For example, a prediction model may be built to predict how FACEBOOK® users may react to a post on FACEBOOK®, while another prediction model is built to predict how TWITTER® users will react to a post on TWITTER®. The posts and responses are gathered from the community site and metrics are calculated for the responses. The calculated metrics may include a number of responses, a number of responses per day, a longevity of a post, a sentiment evoked by the post, and the like. The post and metrics are input into a training module that uses the posts to build the prediction model. Once the model is built, a user may enter a proposed post and receive a prediction of how the proposed post will be received by the community. In some embodiments, suggestions are provided to the user for ways to make the reaction to the proposed post more positive. The model is periodically retrained with new posts and responses retrieved from Internet.

#Posts and responses are gathered from the Internet. A post is any message published on an online forum or newsgroup and may include social posts on social platforms such as FACEBOOK®, TWITTER®, and the like, blogs, or marketing materials posted by enterprise marketers. Responses may be a text response, a “Like” indication, an email, or any published reply to a post. Gathering the posts and responses may involve sending Hyper-text Transfer Protocol (HTTP) requests to retrieve the posts from the Internet. Other data protocols, formats, and sources may also be used to gather posts from the Internet, an intranet, a wired or wireless LAN, WAN, etc.