Abstract: Exemplary methods, apparatuses, and systems generate a social ballot for users within a communication system. Using interactions performed by users within the communication system, the communication system generates a social ballot for a user that includes political questions impacting the user. For example, the communication system identifies users that are impacted by the political issue. The communication system determines a response to a question regarding the political issue for a first user and determines whether a connection between the first user and a second user also impacted by the political issue meets a threshold level of affinity. When the connection between the first user and the second user meets the threshold level of affinity, the communication system generates a ballot for the second user that includes the question regarding the political issue and the response for the first user, and transmits the ballot to the second user.

Abstract: Exemplary methods, apparatuses, and systems generate a civic graph of users within a communication system. Using connections formed within the civic graph, the communication system recommends additional connections between nodes representing constituents and nodes representing political office holders. For example, a request is received from a first user of a communication system to interact with a second user of the communication system. A first node representing the second user is determined to be connected to a second node representing a political office by a first edge, the first edge representing that the second user holds the political office represented by the second node. In response to the received request and the determination that the second user holds the political office, a recommendation is transmitted to the first user, including one or more interface objects enabling the first user to interact with another political office holder in the civic graph.

Abstract: A system and method for automatically generating fluent textual summary from multiple opinions. The opinion summarization system comprises a feature extractor, a text generator and a feature analysis storage. The feature extractor retrieves textual opinions from an opinion database relevant to a predetermined topic and analyzes retrieved textual opinions relevant to the predetermined topic by extracting a plurality of predetermined features from the retrieved textual opinions. The feature analysis storage stores the plurality of predetermined features extracted from the retrieved textual opinions. The text generator generates an opinion summary that summarizes all of the retrieved textual opinions relevant to the predetermined topic by converting the plurality of predetermined features extracted from the retrieved textual opinions into the opinion summary comprising a fluent block of text.