- Armonk NY, US Robert E. Loredo - North Miami Beach FL, US Fang Lu - Billerica MA, US Matthew E. Broomhall - Goffstown NH, US
International Classification:
H04L 12/58 G06N 20/00 H04L 29/08
Abstract:
Conversation slipstream propagation can include using machine learning to construct a conversations graph representing conversations conducted over an electronic communications network by a plurality of participants and collected from one or more messaging platforms. A conversation slipstream comprising one or more communications extracted from the conversations can be generated in response to receiving a secondary communication over the electronic communications network. Each of the one or more communications extracted is represented by a sub-graph of the conversations graph, each sub-graph corresponding to a graph of the secondary communication. The conversation slipstream can be presented to at least one participant to the secondary communication.
- Armonk NY, US Robert E. Loredo - North Miami Beach FL, US Fang Lu - Billerica MA, US Matthew E. Broomhall - Goffstown NH, US
International Classification:
H04L 12/58 H04L 29/08 G06Q 50/00
Abstract:
A processor may analyze one or more social media messages from one or more social media platforms. Each of the one or more social media messages may include a generalized metadata tag and the one or more social media messages may be categorized as a generalized group. The processor may determine, from the generalized group, that the one or more social media messages exceeds a generalized threshold. The processor may generate a first specialized metadata tag for a first set of social media messages included in the one or more social media messages. The processor may partition, based on the first specialized metadata tag, the first set of the one or more social media messages into a specialized group within the generalized group. The processor may direct one or more users associated with the first set of social media messages to the specialized group.
Social-Geofenced-Based Application Management For Battery Maximization
- Armonk NY, US Tushar Kumar Jayantilal - Coppell TX, US Fang Lu - Billerica MA, US Ishwarya Rajendrababu - Hobooken NJ, US
International Classification:
G06F 1/32 H04L 29/08 G06F 9/445
Abstract:
A method, system and computer program product for providing social-geofenced-based application management for battery maximization. Social traffic information is collected for a defined cohort of persons within one or more predefined geofences, wherein the defined cohort of persons is based on one or more individual or group attributes, and the social traffic information includes battery usage for devices used by the defined cohort of persons. The social traffic information is analyzed to classify conditions derived therefrom into one or more categories. Application performance is controlled on a user's device, based on the conditions classified into the categories, to optimize battery usage of the user's device.
Sorting And Displaying Documents According To Sentiment Level In An Online Community
- Armonk NY, US ROBERT E. LOREDO - NORTH MIAMI BEACH FL, US FANG LU - BILLERICA MA, US SUSAN RICERCATO - WESTFORD MA, US ZI SARDONE - CHELMSFORD MA, US
Assignee:
INTERNATIONAL BUSINESS MACHINES CORPORATION - Armonk NY
International Classification:
G06F 17/30 G06F 17/28
Abstract:
An approach is described for sorting and displaying documents according to sentiment level in an online community. An associated system may include a processor and a memory storing an application program, which, when executed on the processor, performs an operation that may include selecting a review topic in an online community and identifying a plurality of documents contributed for the review topic. The plurality of documents may include at least one of a product review submission, a marketing survey submission, a social network activity stream post, a discussion forum post, a weblog post, and an audiovisual sample. The operation further may include obtaining sentiment data associated with each of the plurality of documents developing a sentiment model based on the obtained sentiment data. Additionally, the operation may include organizing and presenting the plurality of documents in an online community interface based on the sentiment model.Page 2
Sorting And Displaying Documents According To Sentiment Level In An Online Community
- ARMONK NY, US ROBERT E. LOREDO - NORTH MIAMI BEACH FL, US FANG LU - BILLERICA MA, US SUSAN RICERCATO - WESTFORD MA, US ZI SARDONE - CHELMSFORD MA, US
International Classification:
G06F 17/30 G06F 17/21
Abstract:
An approach is described for sorting and displaying documents according to sentiment level in an online community. An associated method may include selecting a review topic in an online community and identifying a plurality of documents contributed for the review topic. The plurality of documents may include at least one of a product review submission, a marketing survey submission, a social network activity stream post, a discussion forum post, a weblog post, and an audiovisual sample. The method further may include obtaining sentiment data associated with each of the plurality of documents developing a sentiment model based on the obtained sentiment data. Additionally, the method may include organizing and presenting the plurality of documents in an online community interface based on the sentiment model.
Youtube
Cypress cold case killings: Suspect's arrest ...
It took close to nine years, but authorities believe they have the man...
Duration:
2m 44s
Man accused of killing 4 Cypress family membe...
Feng Lu, 58, is accused of shooting and killing four members of the Su...
Duration:
2m 3s
Judge denies bond for man charged with killin...
Feng Lu is charged with capital murder for the execution-style shootin...
Duration:
1m 49s
Man Wiped Out Boss' Family After Getting Reje...
Fang Lu, 58, now faces capital murder charges for allegedly massacring...
Duration:
7m 15s
No World: Artist Fang Lu in Conversation with...
Join us for a a conversation with artist Fang Lu and Herb Tam, curator...