基于注意力机制与文本信息的用户关系抽取

随着社交媒体的发展,用户之间的关系网络对于社交媒体的分析有很大的帮助。因此,该文主要研究用户好友关系检测。以往的关于用户好友关系抽取的研究主要基于社交媒体上的结构化信息,比如其他好友关系,用户的不同属性等。但是,很多时候用户本身并没有大量的好友信息存在,同时也不一定有很多确定的属性。因此,我们希望基于用户发表的文本信息来对用户关系进行预测。不同于以往的潜在好友推荐算法,该文提出了一种基于注意力机制以及长短时记忆网络(long short-term memory,LSTM)的好友关系预测模型,将好友之间的评论分开处理,通过分析用户之间的评论来判断是否具备一定的好友关系。该模型将好友双方信息拼接后的结果作为输入,并将注意力机制应用于LSTM的输出。实验表明,用户之间的评论对于好友关系预测确实有较大的实际意义,该文提出的模型较之于多个基准系统的效果,取得了明显的提升。在不加入任何其它非文本特征的情况下,实验结果的准确率达到了77%。     

The Emotional Dog Gets Mistaken for a Possum.

H. D. Saltzstein and T. Kasachkoff (2004) (see record 2004-21519-004) critique the social intuitionist model (J. Haidt, 2001) (see record 2001-18918-008), but the model they critique is a stripped-down version that should be called the "possum" model. They make 3 charges about the possum model that are not true about the social intuitionist model: that it includes no role for reasoning, that it reduces social influence to compliance, and that it does not take a developmental perspective. After a defense of the honor of the social intuitionist model, this article raises 2 areas of legitimate dispute: the scope and nature of moral reasoning and the usefulness of appealing to innate ideas, rather than to learning and reasoning, as the origin of moral knowledge. This article presents 3 clusters of innate moral intuitions, related to sympathy, hierarchy, and reciprocity. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Empirical comparison of image retrieval color similarity methods with human judgment

It is important to verify assumptions and methods of image retrieval against actual human behavior. A study was conducted to compare similarity methods of color histograms against human assessment of similarity. The similarity methods tested include basic histogram intersection, center histogram matching, locality histogram matching, and size-weighted histogram matching. 161 subjects participated in the empirical study. The findings, based on Spearman correlation analysis, showed that both the basic histogram intersection method and size-weighted histogram are very close to human assessment of similarity (Spearman correlation coefficient of 0.915). The other two are not close to human judgment on similarity. This study illustrates an alternative approach to evaluating matching algorithms. Unlike the usual measures of recall and precision, this approach emphasizes human validation. Fewer images are required with the use of statistical testing.     

The accuracy of self-monitoring and its relationship to self-focused attention in dysphoria and clinical depression.

The accuracy with which dysphoric (Study 1) and clinically depressed (Study 2) individuals make self-regulatory judgments about their own performance in the absence of external feedback and the extent to which this relates to trait self-focused attention (SFA) were examined. Relative to objective criteria, both dysphoric and depressed participants showed a positive judgment bias, overestimating the number of trials they had performed correctly. Relative to control participants, the dysphoric and depressed groups showed a reduction in the extent of this positive bias in that they judged error trials more accurately and correct trials less accurately. Although the dysphoric and depressed groups both reported elevated trait SFA, this did not correlate significantly with accuracy of self-judgment on the performance-monitoring task. Implications for self-regulation models of depression are discussed. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Judgment: The Foundation of Professional Success.

Lists of core competencies or critical capabilities are popular and plentiful. This article makes the case that a single core competency or critical capability accounts for professional success: the exercise of judgment. Judgment is the critical determinant of the quality of professional decisions, actions, and evaluations. Practical models of judgment are presented. The elements and dynamics of judgment are detailed. Individual, group, and organization implications are explored. Coaching and consulting interventions are explained. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Unintentionally Biasing the Data: Reply to Knobe.

Knobe (2003) wants to help adjudicate the philosophical debate concerning whether and under what conditions we normally judge that some side effect was brought about intentionally. His proposal for doing so is perhaps an obvious one--simply elicit the intuitions of "The Folk" directly on the matter and record the results. Knobe concludes that people's judgment that a side effect was brought about intentionally apparently rests, at least in part, upon how blameworthy they find the agent responsible for it. Knobe's appreciably straightforward approach to this question does not settle the matter, however. Simply raising that question can itself affect our evaluation of the side effect in question as either something good or something bad. As a result, Knobe's experiments effectively bias subjects' responses toward judging the given side effects more negatively than they might have otherwise. Subjects failed to assign a high level of praise for good side effects because taking into account whether they were brought about intentionally or unintentionally makes them suspect. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

激光微焊接质量的模糊识别技术研究

讨论了激光微焊点焊接质量的模糊识别的概念，数学模型及其应用方法，并介绍了系统的硬件组成。     

恢复地层剥蚀厚度方法综述

恢复地层剥蚀厚度是对盆地进行定量研究的重要基础工作。本文综述、评价了目前常用的恢复剥蚀厚度的方法,并对作者曾提出的天然气平衡浓度法作了进一步的阐述。     

Political orientation and modern versus aversive racism: Tests of Dovidio and Gaertner's (1998) integrated model.

According to J. F. Dovidio and S. L. Gaertner's (1998) integrated model of racism, politically liberal European Americans tend to express racism differently than conservative European Americans, with liberals demonstrating aversive racism and conservatives, symbolic or modern racism. In support of the model, in Experiment 1 liberals showed bias in favor of a twice-prosecuted African American relative to a European American in their judgment of double jeopardy, whereas conservatives did the reverse. Experiment 2 replicated these effects while eliminating a confound in the design of Experiment 1. Experiment 3 found evidence for the intrapsychic conflict hypothesized to underlie aversive racism. Specifically, only liberals displayed greater physiological arousal to the touch of an African American versus a European American experimenter. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Teachers' brief nonverbal behaviors in defined instructional situations can predict students' evaluations.

Can a few seconds of high school teachers' nonverbal (NV) behavior predict students' ratings of these teachers (SRT)? Yes, but NV-SRT relations varied among various instructional situations. NV behaviors while administering the class and using the board were unrelated to SRT. Positive judgments of NV behavior while disciplining the class and interacting with students were positively related to SRT. NV behaviors in frontal teaching were negatively related to SRT. The most negative NV-SRT relations were found for teachers' differential NV behavior toward high- versus low-achieving students. Teacher differentiality and SRT have rarely been investigated in high school. The structure of SRT seems to differ between high school and college, and students' anger about teachers' differentiality strongly predicted their evaluations. (PsycINFO Database Record (c) 2010 APA, all rights reserved)