Sequential sampling models of human text classification

Text classification involves deciding whether or not a document is about a given topic. It is an important problem in machine learning, because automated text classifiers have enormous potential for application in information retrieval systems. It is also an interesting problem for cognitive science, because it involves real world human decision making with complicated stimuli. This paper develops two models of human text document classification based on random walk and accumulator sequential sampling processes. The models are evaluated using data from an experiment where participants classify text documents presented one word at a time under task instructions that emphasize either speed or accuracy, and rate their confidence in their decisions. Fitting the random walk and accumulator models to these data shows that the accumulator provides a better account of the decisions made, and a “balance of evidence” measure provides the best account of confidence. Both models are also evaluated in the applied information retrieval context, by comparing their performance to established machine learning techniques on the standard Reuters‐21578 corpus. It is found that they are almost as accurate as the benchmarks, and make decisions much more quickly because they only need to examine a small proportion of the words in the document. In addition, the ability of the accumulator model to produce useful confidence measures is shown to have application in prioritizing the results of classification decisions.     

Bidirectional cognitive computing method supported by cloud technology

To realize the bidirectional cognitive computing supported by cloud technology, the cloud model is taken as a bidirectional cognitive computing model based on probability and statistics, a bidirectional cognitive calculation method is constructed, and the bidirectional cognitive conversion between concept connotation and extension is studied. In view of the defects in the existing backward cloud conversion algorithm, two stable multistep backward cloud conversion algorithms are proposed, which lays the foundation for the realization of a stable bidirectional cognitive calculation process. A bidirectional cognitive computing model is proposed, which combines the characteristics of human cognition and the bidirectional cognitive conversion algorithm to simulate bidirectional cognitive computing process based on concept by means of calculation. Moreover, the application of bidirectional cognitive transform algorithm in image segmentation is studied combined with the characteristics of human image cognition. It is also compared with the classical algorithm and methods based on cloud model. The results show that the proposed method has lower mean error and is obviously better than other algorithms, which fully proves the effectiveness of the method.     

有性Penna模型:进化心理学的新工具

进化心理学家以进化论为基础,使用了许多不同的方法来研究人类的心灵。这些方法都有共同的缺陷,即无法直接对提出的假设进行验证,对复杂的系统进行研究难度很大,计算机模拟的方法可在一定程度上修补该问题。有性Penna模型能反映有性生殖种群的进化特点,能反映环境对生物进化的影响,通过该模型来模拟人类进化历程,则可以检验某一心理机制是否是适应的,它是研究生物进化的有力工具。本文在综述已有研究成果的基础上提出用有性Penna模型对进化心理学关于进化轨迹的假设进行验证的构想,并在此基础之上提出了用该模型进行研究的基本框架。     

What is behind a summary-evaluation decision?

Research in psychology has reported that, among the variety of possibilities for assessment methodologies, summary evaluation offers a particularly adequate context for inferring text comprehension and topic understanding. However, grades obtained in this methodology are hard to quantify objectively. Therefore, we carried out an empirical study to analyze the decisions underlying human summary-grading behavior. The task consisted of expert evaluation of summaries produced in critically relevant contexts of summarization development, and the resulting data were modeled by means of Bayesian networks using an application called Elvira, which allows for graphically observing the predictive power (if any) of the resultant variables. Thus, in this article, we analyzed summary-evaluation decision making in a computational framework.     

An eye-tracking attention based model for abstractive text headline

Online network platforms provide great convenience for users to obtain information. However, it’s challenging to select the required information from enormous texts. Automatic text headline generation methods not only guide users to select the information they are interested in, but also solve the problem of information overload. Nevertheless, the existing works mainly utilize the grammar rules to obtain the key information of the source text, while ignoring the dwell time of user’s attention on different text contents. To address this issue, this paper proposes an abstractive text headline generation model based on the eye-tracking attention mechanism. Specifically, this model first relies on the eye-tracking data to establish the mapping relationship between text words and the words’ reading time. Then, an eye-tracking attention mechanism is constructed to judge the importance of different words. Finally, this attention mechanism is integrated into the encoder-decoder framework to generate a high-quality headline. Experimental results obtained from different datasets demonstrate that the headline generated by our model is more concise. Moreover, our proposed model outperforms significantly the classical headline generation models on ROUGE-1, ROUGE-2 and ROUGE-L.     

Combined eyetracking and keystroke-logging methods for studying cognitive processes in text production

Writers typically spend a certain proportion of time looking back over the text that they have written. This is likely to serve a number of different functions, which are currently poorly understood. In this article, we present two systems, ScriptLog+TimeLine and EyeWrite, that adopt different and complementary approaches to exploring this activity by collecting and analyzing combined eye movement and keystroke data from writers composing extended texts. ScriptLog+TimeLine is a system that is based on an existing keystroke-logging program and uses heuristic, pattern-matching methods to identify reading episodes within eye movement data. EyeWrite is an integrated editor and analysis system that permits identification of the words that the writer fixates and their location within the developing text. We demonstrate how the methods instantiated within these systems can be used to make sense of the large amount of data generated by eyetracking and keystroke logging in order to inform understanding of the cognitive processes that underlie written text production.     

Getting from neuron to checkmark: models and methods in cognitive survey research

Since the 1980s much work has been done in the field of Cognitive Survey Research. In an interdisciplinary endeavour, survey methodologists and cognitive psychologists (as well as social psychologists and linguists) have worked to unravel the cognitive processes underlying survey responses: to improve survey measurement, but also to obtain fundamental insight into the process of question answering, the nature of attitudes, the functioning of human memory, etc. Yet, despite the amount of work that has been done, less progress has been made than was deemed possible. This paper suggests ways in which to develop cognitive theories that may help to obtain an integrated understanding of question answering in surveys. One way to build better theories is to focus on model construction. Different types of cognitive models are discussed that can be used to model question answering. Second, a larger variety of methods from the cognitive toolbox can be used to further develop and test these models. An overview is given of the various tools available to researchers of cognitive aspects of survey research, with a special focus on newer methods from cognitive neuroscience. To connect different tools and methods into an integrative theory of question answering, the idea of hierarchical modelling is proposed. Copyright © 2007 John Wiley & Sons, Ltd.     

文本阅读中协调性整合的发生机制

采用移动窗口技术和自我报告法探讨了文本阅读中协调性整合发生的具体机制。被试为华南师范大学本科生114名。实验1通过分析不同条件下目标句的阅读时间探讨当前信息跟先前信息只有语义相关上的局部不一致但没有事件相关时能否发生协调性整合。实验2通过分析不同条件下探测词的反应时间探讨文本阅读过程中单纯语义相关没有事件相关时,目标句阅读是否会自动激活跟其有关的背景信息。实验3通过分析不同条件下目标句的阅读时间和被试的自我报告指标探讨协调性整合是否是一种自动化的过程,即探讨被试在文本阅读过程中能否意识到这种信息整合方式。总的实验结果表明,文本阅读中当前信息跟先前信息有语义相关时可以引发信息激活,但只有当前信息跟先前信息有事件相关时才会发生信息整合;另外,协调性整合是一种自动化的过程,读者在文本阅读过程中不能意识到这种信息整合方式的发生     

Toward an alternative representation for disentangling age-associated differences in general and specific cognitive abilities

Much of cognitive aging research concerns whether age-associated differences in various cognitive performances can be accounted for by general explanatory constructs or whether several specific processes are involved. Structural equation models have been proposed to disentangle general and specific age-associated differences in cognitive performance. This article demonstrates that existing methods that employ stepwise procedures run the risk of biasing results toward general resource accounts. An alternative model representation (i.e., the nested factor model) is proposed that affords simultaneous estimation of general and specific effects and is applied to data from the Berlin Aging Study. Using the nested factor model allowed the authors to detect that specific group factors explained 25% of the age-associated variance in addition to the general factor.     

Assessing short summaries with human judgments procedure and latent semantic analysis in narrative and expository texts

In the present study, we tested a computer-based procedure for assessing very concise summaries (50 words long) of two types of text (narrative and expository) using latent semantic analysis (LSA) in comparison with the judgments of four human experts. LSA was used to estimate semantic similarity using six different methods: four holistic (summary-text, summary-summaries, summary-expert summaries, and pregraded-ungraded summary) and two componential (summary-sentence text and summary-main sentence text). A total of 390 Spanish middle and high school students (14–16 years old) and six experts read a narrative or expository text and later summarized it. The results support the viability of developing a computerized assessment tool using human judgments and LSA, although the correlation between human judgments and LSA was higher in the narrative text than in the expository, and LSA correlated more with human content ratings than with human coherence ratings. Finally, the holistic methods were found to be more reliable than the componential methods analyzed in this study.     

Integrating a cognitive computational model of planning and decision-making considering affective information

Planning and decision-making are two of the cognitive functions involved in the solution of problems. These functions, among others, have been studied from the point of view of a new field known as cognitive informatics focused on the development of cognitive architectures, autonomous agents, and human robots that are capable of showing human-like behavior. We present an exhaustive study of current biological and computational models proposed in the fields of neuroscience, psychology, and cognitive informatics. Also, we present a deep review of the brain areas involved in planning, decision-making, and affection. However, the majority of the proposed computational models are seeking to mimic human external behavior. This paper aims to contribute to the cognitive informatics field with an innovative cognitive computational model of planning and decision-making. The two main differences of our model with respect to the current models in the literature are: (i) our model considers affective and motivational information as a basic and essential trigger in planning and decision-making processes; (ii) our model attempts to mimic both the internal human brain as well as the external human behavior. We developed a computational model capable of offering a direct mapping from human brain areas to computational modules of our model. Thus, in this paper we present our model from a conceptual, formal, and computational approach in order to show how our proposal must be implemented. Finally, a set of tests were conducted in order to validate our proposal. These tests show an interesting comparison between the behavior of our prototype and the behavior exhibited by some people involved in a case study.     

A Class of Population Covariance Matrices in the Bootstrap Approach to Covariance Structure Analysis

Model evaluation in covariance structure analysis is critical before the results can be trusted. Due to finite sample sizes and unknown distributions of real data, existing conclusions regarding a particular statistic may not be applicable in practice. The bootstrap procedure automatically takes care of the unknown distribution and, for a given sample size, also provides more accurate results than those based on standard asymptotics. But the procedure needs a matrix to play the role of the population covariance matrix. The closer the matrix is to the true population covariance matrix, the more valid the bootstrap inference is. The current paper proposes a class of covariance matrices by combining theory and data. Thus, a proper matrix from this class is closer to the true population covariance matrix than those constructed by any existing methods. Each of the covariance matrices is easy to generate and also satisfies several desired properties. An example with nine cognitive variables and a confirmatory factor model illustrates the details for creating population covariance matrices with different misspecifications. When evaluating the substantive model, bootstrap or simulation procedures based on these matrices will lead to more accurate conclusion than that based on artificial covariance matrices.     

Twitter sentiment analysis with a deep neural network: An enhanced approach using user behavioral information

Sentiment analysis on social media such as Twitter has become a very important and challenging task. Due to the characteristics of such data—tweet length, spelling errors, abbreviations, and special characters—the sentiment analysis task in such an environment requires a non-traditional approach. Moreover, social media sentiment analysis is a fundamental problem with many interesting applications. Most current social media sentiment classification methods judge the sentiment polarity primarily according to textual content and neglect other information on these platforms. In this paper, we propose a neural network model that also incorporates user behavioral information within a given document (tweet). The neural network used in this paper is a Convolutional Neural Network (CNN). The system is evaluated on two datasets provided by the SemEval-2016 Workshop. The proposed model outperforms current baseline models (including Naive Bayes and Support Vector Machines), which shows that going beyond the content of a document (tweet) is beneficial in sentiment classification, because it provides the classifier with a deep understanding of the task.     

文本检索模型综述

文本检索是信息检索一个重要的分支。随着互联网信息的迅速膨胀,如何检索到用户最需要的信息变得越来越关键。文本检索模型是文本检索中的核心技术,其性能直接影响到搜索引擎的检索质量。本文对当前的经典检索模型及其研究进展进行介绍,并分析各个模型之间的优缺点。     

Testing the cognitive relevance of a geometric model on a word association task: A comparison of humans, ACOM, and LSA

The general aim of this study is to validate the cognitive relevance of the geometric model used in the semantic atlases (SA). With this goal in mind, we compare the results obtained by the automatic contexonym organizing model (ACOM)—an SA-derived model for word sense representation based on contextual links—with human subjects’ responses on a word association task. We begin by positioning the geometric paradigm with respect to the hierarchical paradigm (WordNet) and the vector paradigm (latent semantic analysis [LSA] and the hyperspace analogue to language model). Then we compare ACOM’s responses with Hirsh and Tree’s (2001) word association norms based on the responses of two groups of subjects. The results showed that words associated by 50% or more of the Hirsh and Tree subjects were also proposed by ACOM (e.g., 71% of the words in the norms were also given by ACOM). Finally, we compare ACOM and LSA on the basis of the same association norms. The results indicate better performance for the geometric model.     

Identifying influential segments from word co-occurrence networks using AHP

Identifying important segments in textual data seems to be an important area of research for various applications including topic modelling, trend detection, summarization and event detection. In existing research work, different metrics have been studied to analyse the word co-occurrence network. This research work contributes towards non-semantic and an unsupervised topic identification using the word co-occurrence networks. In this research work, keyphrase have been identified by preserving the lexical sequence using a directed and weighted word co-occurrence network. Further AHP (Analytic Hierarchy Process) model based upon four significant attributes of the word co-occurrence networks have been proposed to rank the keyphrases. Most frequently occurring segment is identified as an influential segment. Experimental results proved high effectiveness of the proposed approach. Results for the First Story Detection, 72 Twitter TDT, synthesized Rio Olympics dataset have been discussed to demonstrate its potential in precisely discovering influential segments.     

Understanding user’s travel behavior and city region functions from station-free shared bike usage data

Station-free shared bike (SFSB) is a new travel mode that shared bikes are allowed to park in any proper places. It implies that the users are more likely to park the SFSB as close as their destinations. This advantage makes the SFSB data to be an ideal source to understand the land-use distribution. Inspired by the idea in text mining, this paper proposes a topic-based two-stage SFSB data mining algorithm to understand the SFSB user’s travel behavior and to discover city functional regions. A region, a function and human mobility patterns are treated as a document, a topic and words, respectively. Then, a region is represented by a distribution of functions, and a function is featured by a distribution of mobility patterns. The point-of-interest data is combined to annotate the clustered regions to discover the real functions. At last, the proposed method is tested using 14-day SFSB data in Beijing and the results are estimated by the Satellite Map data. The proposed methods and the results can be applied to infer the individual’s travel purpose through functional regions and to improve land-use planning, etc.     

文本信息加工中的知识结构的测量

知识结构是信息加工中各类信息在记忆系统中的组织结构的反映。为更好地表征和分析知识结构,研究者从教育科学技术和计算机技术的角度发展出一系列的研究方法和测量工具,包括潜在语义分析、心理模型分析和语义聚合分析。研究者可以结合具体情况选用合适的测量工具。而如何实现眼动、功能性成像数据与当前的测量相结合,则需要研究者在未来的工作中展开进一步探讨。     

A note on epistemics and discourse analysis

Discursive Psychology has the great merit of having introduced discourse analysis (DA) to social psychology and to have contributed to DA itself by its study of the expression of 'psychological' notions in text and talk. Within this perspective, this paper presents some elements of a proposal to study the expression of knowledge in discourse. Beginning with a brief summary of our multidisciplinary approach to knowledge, followed by a summary of discourse structures that express knowledge, the main argument of the paper is that we not only need to take discourse seriously in the study of knowledge, but cannot ignore their cognitive underlying structures if we want to describe and explain many properties of discourse, such as all implicit or presupposed knowledge, as well as the interactional and contextual management of old and new knowledge in text and talk.     

文本阅读双加工理论与实验证据

文本阅读信息加工过程研究一直是国内外心理学界高度重视和关注的领域, 形成了建构主义理论、最低限度假设理论和记忆基础文本加工理论等派别百家争鸣的局面。这些理论争议的焦点在于自然阅读是主动的、积极的、目标策略驱动的过程, 还是被动的、消极的、自动的过程。在全面总结国内外心理学界有关文本阅读的研究成果的基础上, 文本阅读双加工理论提出并对文本阅读的主要争议进行了整合。该理论的核心观点是文本的自然阅读过程是连贯阅读与焦点阅读的双加工过程。文本阅读中读者所阅读的材料特点不同, 引发的阅读信息加工活动也不同, 而不同性质的阅读过程, 又会引发不同的推理整合, 从而会建构不同类型的文本表征。文本阅读双加工理论已经形成了比较完整的理论框架, 并获得了很多实验证据的支持。当然, 文本阅读双加工理论作为一个新的理论, 其中的有些观点还需要进一步检验。在未来的文本阅读研究领域, 有很多问题还需要研究者进一步关注。