Co-PoeTryMe: Interactive poetry generation

PoeTryMe is a poetry generation system that autonomously produces poems from a set of initial parameters. After using it, creative writers and other users of this system expressed the desire to partake in the creative process by directly interacting with PoeTryMe. This paper is motivated by the previous impressions. It illustrates some of the challenges of automatic poetry generation, highlights limitations of PoeTryMe, and reports on recent efforts to address user feedback and provide alternative ways of using this system. First, making some functionalities available via a web API enabled their exploitation by other systems. Those include the generation of single lines as well as retrieval of related words, allowing for additional constraints on the number of syllables, sentiment and rhyme. On top of this API, a co-creative interface, Co-PoeTryMe, has been developed. Co-PoeTryMe allows users to either start from scratch or from a generated draft. Extensive editing functionality has been incorporated, in particular, allowing lines and words to be switched or replaced by newly generated alternatives. Co-PoeTryMe, its interface and the co-creative process for producing poetry are described, along with a user study that provided useful feedback. Users pointed out the strengths of this new system, including its capacities in providing inspiration, and giving the user the ability to customize an existing draft and visualize the changes, but also pointed out weaknesses, primarily by identifying potential improvements in the user interface.     

结合题目作答时间的计算机化自适应测验选题方法

计算机形式的测验能够记录考生在测验中的题目作答时间（Response Time, RT），作为一种重要的辅助信息来源，RT对于测验开发和管理具有重要的价值，特别是在计算机化自适应测验（Computerized Adaptive Testing, CAT）领域。本文简要介绍了RT在CAT选题方面应用并作以简评，分析了这些技术在实践中的可行性。最后，探讨了当前RT应用于CAT选题存在的问题以及可以进一步开展的研究方向。     

Problems with Rationales for Parceling that Fail to Consider Parcel-Allocation Variability

In structural equation modeling applications, parcels—averages or sums of subsets of item scores—are often used as indicators of latent constructs. Parcel-allocation variability (PAV) is variability in results that arises within sample across alternative item-to-parcel allocations. PAV can manifest in all results of a parcel-level model (e.g., model fit, parameter estimates, standard errors, and inferential decisions). It is a source of uncertainty in parcel-level model results that can be investigated, reported, and accounted for. Failing to do so raises representativeness and replicability concerns. However, in recent methodological literature (Cole, Perkins, &; Zelkowitz, 2016 Cole, D. A., Perkins, C. E., &; Zelkowitz, R. L. (2016). Impact of homogeneous and heterogeneous parceling strategies when latent variables represent multidimensional constructs. Psychological Methods, 21(2), 164–174. doi: 10.1037/met0000047[Crossref], [PubMed], [Web of Science ®] , [Google Scholar]; Little, Rhemtulla, Gibson, &; Shoemann, 2013 Little, T. D., Rhemtulla, M., Gibson, K., &; Schoemann, A. M. (2013). Why the items versus parcels controversy needn't be one. Psychological Methods, 18(3), 285–300. doi: 10.1037/a0033266[Crossref], [PubMed], [Web of Science ®] , [Google Scholar]; Marsh, Ludtke, Nagengast, Morin, &; von Davier, 2013 Marsh, H. W., Lüdtke, O., Nagengast, B., Morin, A., &; von Davier, M. (2013). Why item parcels are (almost) never appropriate: Two wrongs do not make a right—camouflaging misspecification with item parcels in CFA models. Psychological Methods, 18(3), 257–284. doi: 10.1037/a0032773[Crossref], [PubMed], [Web of Science ®] , [Google Scholar]; Rhemtulla, 2016 Rhemtulla, M. (2016). Population performance of SEM parceling strategies under measurement and structural model misspecification. Psychological Methods, 21(3), 348–368. doi: 10.1037/met0000072[Crossref], [PubMed], [Web of Science ®] , [Google Scholar]) parceling has been justified and recommended in several situations without quantifying or accounting for PAV. In this article, we explain and demonstrate problems with these rationales. Overall, we find that: (1) using a purposive parceling algorithm for a multidimensional construct does not avoid PAV; (2) passing a test of unidimensionality of the item-level model need not avoid PAV; and (3) a desire to improve power for detecting structural misspecification does not warrant parceling without addressing PAV; we show how to simultaneously avoid PAV and obtain even higher power by comparing item-level models differing in structural constraints. Implications for practice are discussed.     

Using Response Times for Joint Modeling of Response and Omission Behavior

Abstract

For adequate modeling of missing responses, a thorough understanding of the nonresponse mechanisms is vital. As a large number of major testing programs are in the process or already have been moving to computer-based assessment, a rich body of additional data on examinee behavior becomes easily accessible. These additional data may contain valuable information on the processes associated with nonresponse. Bringing together research on item omissions with approaches for modeling response time data, we propose a framework for simultaneously modeling response behavior and omission behavior utilizing timing information for both. As such, the proposed model allows (a) to gain a deeper understanding of response and nonresponse behavior in general and, in particular, of the processes underlying item omissions in LSAs, (b) to model the processes determining the time examinees require to generate a response or to omit an item, and (c) to account for nonignorable item omissions. Parameter recovery of the proposed model is studied within a simulation study. An illustration of the model by means of an application to real data is provided.     

Effects of multiple versus chained schedules on stereotypy and item engagement

We evaluated rates of automatically reinforced stereotypy and item engagement for 2 children with autism under multiple and chained schedules in a multielement design. Each schedule included components during which stereotypy was blocked (S–) or allowed (S+), and we used colored cards as schedule‐correlated stimuli. We report rates of stereotypy and item engagement during S– and S+ components, as well as the percentage of component time that elapsed before the first instances of stereotypy and item engagement. We observed less stereotypy and more consistent item engagement during chained‐schedule sessions, and stimulus control of stereotypy and item engagement was established with the chained schedule. A subsequent concurrent‐chains analysis revealed participant preference for the chained schedule. These results highlight the importance of contingent access to stereotypy when therapists attempt to gain stimulus control of stereotypy and increase functional item engagement.     

Cognition and emotion: on paradigms and metaphors

ABSTRACT

The field of cognition and emotion is characterised as the cognitive psychology of evaluative and affective processes. The most important development in this field is the fruitful adoption of cognitive psychology paradigms to study automatic evaluation processes, for example. This has led to a plethora of findings and theories. Two points are emphasised: First, the (often metaphorical) theoretical way of thinking has changed over the decades. Theorising with symbolic models (e.g. semantic networks), which was prevalent in earlier years, has been replaced more recently by subsymbolic models (i.e. PDP models). It is argued that – despite their still metaphorical character – the latter are better suited to capturing characteristics of emotional processes. Second, the field has adopted the methods of experimental cognitive psychology to develop and refine paradigms as “windows to the mind”.     

Generation and evaluation of user tailored responses in multimodal dialogue

When people engage in conversation, they tailor their utterances to their conversational partners, whether these partners are other humans or computational systems. This tailoring, or adaptation to the partner takes place in all facets of human language use, and is based on a mental model or a user model of the conversational partner. Such adaptation has been shown to improve listeners’ comprehension, their satisfaction with an interactive system, the efficiency with which they execute conversational tasks, and the likelihood of achieving higher level goals such as changing the listener’s beliefs and attitudes. We focus on one aspect of adaptation, namely the tailoring of the content of dialogue system utterances for the higher level processes of persuasion, argumentation and advice-giving. Our hypothesis is that algorithms that adapt content for these processes, according to a user model, will improve the usability, efficiency, and effectiveness of dialogue systems. We describe a multimodal dialogue system and algorithms for adaptive content selection based on multi-attribute decision theory. We demonstrate experimentally the improved efficacy of system responses through the use of user models to both tailor the content of system utterances and to manipulate their conciseness.     

Whose picture is this? Children's memory for item and source information

Children aged 3½ to 6½ years viewed pictures of common objects presented either once or three times on one of two consecutive days. A different hand puppet was used to present the pictures on each day, providing both perceptual and temporal cues to source. At test, old (studied) and new (non‐studied) pictures were presented for item recognition and source identification. Results showed that both item and source accuracy were higher for older (M = 5; 9 years) than younger children (M = 4; 6 years). Significant interactions between Age and Day of study were found for both item and source accuracy. For younger children, accuracy was higher for pictures studied on Day 1 than Day 2 (significant for source identification but not item recognition), whereas older children showed the opposite pattern: Higher accuracy for Day 2 than Day 1 (significant for item recognition but not source identification). Results are interpreted with respect to proactive interference and response bias. The utility of signal detection theory measures in determining the basis of age differences in performance of source identification is discussed.     

The Relationship between Response-Time Effort and Accuracy in PISA Science Multiple Choice Items

The study examined the relationship between examinees’ test-taking effort and their accuracy rate on items from the PISA 2015 assessment. The 10% normative threshold method was applied on Science multiple-choice items in the Cyprus sample to detect rapid guessing behavior. Results showed that the extent of rapid guessing across simple and complex multiple-choice items was on average less than 6% per item. Rapid guessers were identified, and for most items their accuracy was lower than the accuracy for students engaging in solution-based behavior. A number of plausible explanations were graphically evaluated for items for which accuracy was higher for the rapid guessing subgroup. Overall, this empirical investigation presents original evidence on test-taking effort as measured by response time in PISA items and tests propositions of Wise’s (2017 Wise, S. L. (2017). Rapid‐guessing behavior: Its identification, interpretation, and implications. Educational Measurement: Issues and Practice, 36(4), 52–61. doi:10.1111/emip.12165[Crossref], [Web of Science ®] , [Google Scholar]) Test-Taking Theory.