International Business Machines Corporation

Airbnb, Inc.

Simon P O'Doherty

Liam S Harpur

Al Chakra

Daniel John McCloskey

David M Curran

Stephen A Davies

Robert E Loredo

Di Wu

WuMi Zhong

Huan Zhang

Maria Abu-Saba

John Rice

Sean Callanan

Brian O'Donovan

Brendan P Arthurs

Agnia Barsukova

Alastair G R Cross

Cormac O'Leary

Beng Kong Yap

C Patrick Bakekolo

Romeo Gamulescu

Kioso Mutambwir

Scott P Joynt

Michael Ferris

An approach is described for addressing propagation of inaccurate information in a social networking environment. An associated method may include identifying inaccurate information within the social networking environment, facilitating creation of countering content to address the inaccurate information, and disseminating the countering content. The countering content may be determined by identifying behavior of one or more users among a plurality of users within the social networking environment. Identifying the inaccurate information within the social networking environment may include receiving information provided within the social networking environment. Upon determining that the received information is factual and thus objectively verifiable, it may be determined whether the received information matches analogous information verified as accurate. Upon determining that the received information does not match the analogous information verified as accurate, the received information may be marked as inaccurate.

Addressing propagation of inaccurate information in a social networking environment

Socially provided context-based messaging can include receiving a message content in a messaging system from a user, wherein the content includes objects; matching one or more objects of the message content to socially provided context information, which the socially provided context information is information relevant to an object obtained from a social network to which the user belongs; and displaying the socially provided context information with the message content for a recipient user to receive.

Context-based messaging system

In an approach for modifying a user interface for a user of an application, a processor receives a plurality of actions for a user of an application. A processor generates a unique identifier for each action of the plurality of actions. A processor generates a unique string of the generated unique identifiers for each action of the plurality of actions. A processor determines that a portion of a pattern of the unique string matches, within a predetermined threshold, a portion of a pattern of a history of usage of a set of users of the application. A processor modifies a user interface of the application, for the user, based on the portion of the pattern of the matched unique string, within the predetermined threshold, the portion of the pattern of the history of usage.

Modifying application functionality based on usage patterns of other users

Mechanisms are provided for assembling natural language user inputs into questions for a question-and-answer (QA) system. The mechanisms initialize a timer to a threshold amount of time, receive a first input of content-bearing natural language from a user computing device, and initiate running of the timer in response. The mechanisms determine whether a second input of content-bearing natural language is received from the user computing device prior to the threshold amount of time being reached by the timer. If so, the second input is grouped with the first input to generate a question comprising content of both the first input and the second input, and the timer is reset. In response to the timer reaching the threshold without further input from the user computing device, the question is provided to the QA system as an input question for processing by the QA system.

Question pre-processing in a question and answer system

Concepts for protecting domain-specific language of a dialogue service are presented. The presence of a protected term in a domain-specific query may be identified based on the domain that is specific to the query. The identified protected term may then be substituted with an associated substitute term.

Protecting domain-specific language of a dialogue service

A mechanism is provided for controlling the content of an electronic message on an electronic messaging system including a plurality of communities that facilitates the tailoring of the content of a posted electronic message to the interests and/or access privileges of such communities. An electronic lexicon is provided for each community, the lexicon defining content relevant to the community. The electronic message is interpreted for disclosure to a particular community to identify content in the message relating to content in the electronic lexicon of the particular community. The electronic message is redacted based on the identified related content if the electronic message contains content in a form unsuitable for the disclosure.

Electronic message redacting

A method, computer program product, and system is described. A communication session transcript is identified. A chat session input is received. The chat session input is associated with an inactive portion of the communication session transcript. The chat session input is provided to a recipient, in context with the inactive portion of the communication session transcript.

Historical context for communication

A method, system and computer program product for assisting users to generate the desired meme in a document. A document is scanned to identify parts of speech, numerical text or numbers and images (collectively the 'terms') that provide positive/negative memes. A score for each of these terms is assigned. A score may then be assigned to each designated primary object (e.g., individual, company) discussed in the document using the scores assigned to the identified terms. Options may then be provided to modify the document to provide the type of meme (e.g., positive or negative meme) desired by the author to be associated with the particular designated primary object. Upon receiving a selection of one or more of these options, the document is modified accordingly to generate the desired meme in the document.

Assisting users to generate desired meme in document

Growing community of inventors

Dublin, Ireland

Simon P O'Doherty