Abstracts from Selected Patents and Publications
Benyamin, D., & Blackwell, A., 2013
Systems and methods in accordance with embodiments of the invention can automatically generate advertising campaigns on an online social network using affinity information collected concerning members of one or more online social networks. In one embodiment, a method of targeting a piece of content as a paid advertisement within an online social network includes retrieving metrics with respect to engagement by members of an online social network, determining user affinities based upon the retrieved metrics, determining demographics of members of the online social network that have engaged with the pieces of content, identifying at least one cluster of members of the online social network based on the demographics, where the members are clustered based upon targeting information, and targeting at least one of the specific pieces of content as a paid advertisement targeted based on targeting information.
Benyamin, D., Hall, M., Chu, A. & Blackwell, A., 2012
Systems and methods for automatically targeting advertising on an online social network using affinity information collected concerning members of one or more online social networks in accordance with embodiments of the invention are disclosed. One embodiment of the invention includes a targeting server configured to obtain data from at least one server that forms part of an online social network, where the obtained data describes member profiles of members of the online social network and activities performed on the online social network associated with the member profiles. In addition, the targeting server is configured to detect affinities between a member profile and keywords based upon data describing activities associated with the member profile and to provide the targeting keywords to a server that is part of the online social network so that the online social network displays the specific offer to online social network members targeted using the targeting keywords.
Benyamin, D., Chu, A., Pollock, A., Hall, M. & Blackwell, A. 2012
Systems and methods for automatically generating targeting information for presentation of an offer via an online social network using affinity information collected concerning members of online social networks in accordance with embodiments of the invention are disclosed. One embodiment includes indexing member profiles within social networks for affinity to keywords using a targeting system that retrieves data concerning member profiles and activities from servers within an online social network, identifying member profiles that have affinity for at least one offer keyword using the targeting system and the index, identifying additional keywords for which the identified member profiles have affinity using the targeting system and the index, determining a set of keywords that target a desired audience based upon the identified additional keywords, and targeting presentation of advertisements for the specific offer to members of an online social network using the online social network and the targeting keywords.
Blackwell, Bates, & Fisher, 1996
Two experiments investigating the time course of grammaticality judgement are presented. Sentences vary along three dimensions: error type, location of error, and part of speech. Experiment One is a word-by-word “gating” experiment, similar to the gating paradigm of Grosjean (1980). Experiment Two is an “on-line,” serial visual presentation of the same sentences to different subjects.
Experiment One shows that for some error types there is considerable inter-subject variability in deciding the error point. Experiment Two shows that there are differences in the speed with which decisions are made for different error types. The significance of these results in relation to the Competition Model of Bates and MacWhinney, and parallel distributed processing models, is discussed.
Various predictions of the Competition Model, a theory of on-line language acquisition and processing (Bates and MacWhinney, 1989) are tested, using the MAL (Miniature Artificial Language) paradigm with both humans and multi-layer neural networks.
Humans were tested in a series of different dialects of an MAL with regular syntactic and morphological rules which could also be used as cues to the meaning of the sentence. The variables manipulated included the frequency of the cue, the reliability of the information it offered, and the surface form of the cue (i.e., word order, agreement morphology, or animacy).
In some conditions, subjects’ performance followed the predictions of the Competition Model and profiles seen in child language acquisition, in that their performance initially showed sensitivity to those cues which were more frequent, and then converged later in training upon those cues which were more reliable. However, this effect interacted with the form of the cue in that subjects overall had a more difficult time using agreement morphology than word order, a finding also seen in natural language processing.
Neural networks were tested with languages that were similar in their underlying structure to the MALs used with humans; some versions of the networks showed the same effects as predicted and as seen in normals in that they initially showed sensitivity to those cues which were more frequent, and then converged later in training upon those cues which were more reliable. This effect interacted in an interesting way with the type of network, in that networks with an additional “hidden” layer of processing units were closer to the predicted performance than those with only one layer, even though the one layer networks were well able to solve the problem, suggesting an additional constraint on the types of models that can be used if they are to be psychologically valid.
Implications for the Competition Model and for further research with MALs and their relevance to natural language acquisition are discussed, as well as the useful parallels between MAL research with humans and neural network models.
Blackwell & Bates, 1995
The selective vulnerability of morphology in agrammatic aphasia is often interpreted as evidence that closed-class items reside in a particular part of the brain (i.e., Broca’s area); thus, damage to a part of the language processor maps onto behavior in a transparent fashion. We propose that the selective vulnerability of grammatical morphemes in receptive processing may be the result of decrements in overall processing capacity, and not the result of a selective lesion.
We demonstrate agrammatic profiles in healthy adults who have their processing capacity diminished by engaging in a secondary task during testing. Our results suggest that this selective profile does not necessarily indicate the existence of a distinct sub-system specialized for the implicated aspects of syntax, but rather may be due to the vulnerability of these forms in the face of global resource diminution, at least in grammaticality judgment.