Does More Context Help? Effects of Context Window and Application Source on Retrieval Performance

We study the effect of contextual information obtained from a user’s digital trace on Web search performance. Contextual information is modeled using Dirichlet–Hawkes processes (DHP) and used in augmenting Web search queries. The context is captured by monitoring all naturally occurring user behavior using continuous 24/7 recordings of the screen and associating the context with the queries issued by the users. We report a field study in which 13 participants installed a screen recording and digital activity monitoring system on their laptops for 14 days, resulting in data on all Web search queries and the associated context data. A query augmentation (QAug) model was built to expand the original query with semantically related terms. The effects of context window and source were determined by training context models with temporally varying context windows and varying application sources. The context models were then utilized to re-rank the QAug model. We evaluate the context models by using the Web document rankings of the original query as a control condition compared against various experimental conditions: (1) a search context condition in which the context was sourced from search history; (2) a non-search context condition in which the context was sourced from all interactions excluding search history; (3) a comprehensive context condition in which the context was sourced from both search and non-search histories; and (4) an application-specific condition in which the context was sourced from interaction histories captured on a specific application type. Our results indicated that incorporating more contextual information significantly improved Web search rankings as measured by the positions of the documents on which users clicked in the search result pages. The effects and importance of different context windows and application sources, along with different query types are analyzed, and their impact on Web search performance is discussed.

Conceptual blending and (im)politeness in political cartooning

This paper is meant to give an account of multimodal (im)politeness in political cartoons, drawing primarily on critical discourse studies (CDS) (in particular, Teun van Dijk’s notion of “context models” and Paul Chilton’s concept of “critical discourse moments”), blending theory (Fauconnier and Turner 2002), and speech act theory (especially Geoffrey Leech’s most recent revisions of Penelope Brown and Stephen C. Levinson’s notions of negative and positive face). There is of course an abundant literature on blending theory, but the potential of this theory for analysing face-enhancing or face-threatening multimodal discourse has not been fully realised. It is shown that political cartoons can exemplify not only face attack but also face enhancement, and that blending theory can contribute to the comprehending and critique of sociopolitical action or linguistic and nonlinguistic forms of control that may operate in the world. The article thus demonstrates the value that results from merging critical cognitive linguistics and sociopragmatics.

In for a penny, in for a pound: examining motivated memory through the lens of retrieved context models

When people encounter items that they believe will help them gain reward, they later remember them better than others. A recent model of emotional memory, the emotional context maintenance and retrieval model (eCMR), predicts that these effects would be stronger when stimuli that predict high and low reward can compete with each other during both encoding and retrieval. We tested this prediction in two experiments. Participants were promised £1 for remembering some pictures, but only a few pence for remembering others. Their recall of the content of the pictures they saw was tested after 1 min and, in experiment 2, also after 24 h. Memory at the immediate test showed effects of list composition. Recall of stimuli that predicted high reward was greater than of stimuli that predicted lower reward, but only when high- and low-reward items were studied and recalled together, not when they were studied and recalled separately. More high-reward items in mixed lists were forgotten over a 24-h retention interval compared with items studied in other conditions, but reward did not modulate the forgetting rate, a null effect that should be replicated in a larger sample. These results confirm eCMR's predictions, although further research is required to compare that model against alternatives.

Fall Detection of Elderly People Using the Manifold of Positive Semidefinite Matrices

Falls are one of the most critical health care risks for elderly people, being, in some adverse circumstances, an indirect cause of death. Furthermore, demographic forecasts for the future show a growing elderly population worldwide. In this context, models for automatic fall detection and prediction are of paramount relevance, especially AI applications that use ambient, sensors or computer vision. In this paper, we present an approach for fall detection using computer vision techniques. Video sequences of a person in a closed environment are used as inputs to our algorithm. In our approach, we first apply the V2V-PoseNet model to detect 2D body skeleton in every frame. Specifically, our approach involves four steps: (1) the body skeleton is detected by V2V-PoseNet in each frame; (2) joints of skeleton are first mapped into the Riemannian manifold of positive semidefinite matrices of fixed-rank 2 to build time-parameterized trajectories; (3) a temporal warping is performed on the trajectories, providing a (dis-)similarity measure between them; (4) finally, a pairwise proximity function SVM is used to classify them into fall or non-fall, incorporating the (dis-)similarity measure into the kernel function. We evaluated our approach on two publicly available datasets URFD and Charfi. The results of the proposed approach are competitive with respect to state-of-the-art methods, while only involving 2D body skeletons.

Parallel processing in speech perception: Local and global representations of linguistic context

Speech processing is highly incremental. It is widely accepted that listeners continuously use the linguistic context to anticipate upcoming concepts, words and phonemes. However, previous evidence supports two seemingly contradictory models of how predictive cues are integrated with bottom-up evidence: Classic psycholinguistic paradigms suggest a two-stage model, in which acoustic input is represented fleetingly in a local, context-free manner, but quickly integrated with contextual constraints. This contrasts with the view that the brain constructs a single unified interpretation of the input, which fully integrates available information across representational hierarchies and predictively modulates even earliest sensory representations. To distinguish these hypotheses, we tested magnetoencephalography responses to continuous narrative speech for signatures of unified and local predictive models. Results provide evidence for some aspects of both. Local context models, one based on sublexical phoneme sequences, and one based on the phonemes in the current word alone, do uniquely predict some part of early neural responses; at the same time, even early responses to phonemes also reflect a unified model that incorporates sentence level constraints to predict upcoming phonemes. Neural source localization places the anatomical origins of the different predictive models in non-identical parts of the superior temporal lobes bilaterally, although the more local models tend to be right-lateralized. These results suggest that speech processing recruits both local and unified predictive models in parallel, reconciling previous disparate findings. Parallel models might make the perceptual system more robust, facilitate processing of unexpected inputs, and serve a function in language acquisition.

A Proposed Ontology-Based Generic Context Model for Ubiquitous Learning

Context modeling is the keystone to enable the intelligent system to adapt its functionalities properly to different situations. As such, a representation mechanism that allows an adequate manipulation of this kind of information is required, and diverse approaches have been introduced; however, what takes more value and is being positioned as a standard is the ontology-based context modeling because it presents a common understanding vocabulary for a specific domain. Hence, it might be beneficial to have a generic ontology to model context in this area. However, according to diverse works, there is no proposal of a generic context model for context-aware learning. For addressing this problem, several existing context models are studied to identify the essentials of context modeling, whereby an ontology-based generic context model is presented. The proposed ontology is evaluated in two ways. Firstly, scenarios are used to justify the feasibility of the model; then a comparative study and evaluation metrics are applied to assess the proposal.

Participant’s Roles and Cognitive Relations in Niger Delta Conflict News Discourse

Media studies on Niger Delta (ND) conflict discourse have largely utilized stylistic, pragmatic, and critical discourse analytical tools in exploring media representation of news actors and ideologies in news texts but have not accommodated such issues as participants’ roles and cognitive relations in the discourse. This paper analyses the contexts of ND conflict news reporting with a view to revealing not only the participant’s role relations involved, but also the lexico-semantic resources they are characterized by. Forty newspaper reports on ND conflicts (20 from four ND-based newspapers— The Tide, New Waves, The Pointer and Pioneer, and 20 from four national newspapers— The Punch, The Guardian, Vanguard and THISDAY), published between 2003 and 2009, were sampled and subjected to discourse analysis, with insights from van Dijk’s context models and aspects of relational semantics. Four types of role were identified, viz. interactional (embracing the participants in conflict), communicative (relating to the production roles), social (involving group membership), and instrumental (dealing with the entities utilized in actualizing specific goals). The cognitive foci of these roles are associated with participants’ goals and beliefs, and these inform the participants’ position and hence role in the conflict events. Linguistically, the interactional and social roles are marked by synonymous and converse lexical items, while the communicative and instrumental roles are indexed by homonymous and antonymous lexical features. The findings corroborate the fact that there is an interaction between participant roles and cognitive relations in the ND conflict events reported in Nigerian newspapers.

Understanding breastfeeding behaviours: a cross-sectional analysis of associated factors in Ireland, the United Kingdom and Australia

Background Breastfeeding is a complex behaviour relying on a combination of individual mother and infant characteristics, health systems, and family, community and professional support. Optimal breastfeeding in high-income countries is particularly low. Despite having similar sociocultural backgrounds, breastfeeding rates between Ireland, the United Kingdom (UK) and Australia vary, thus there is a need to understand whether this is due to individual, sociocultural or policy differences. This research identifies the between-country differences in infant feeding mode and examines if country differences in feeding mode persist once known individual, behavioural and structural factors are considered using socioecological and person-context models. Methods Participants were adult women with at least one infant less than 6 months of age, who completed an online survey (n = 2047) that was distributed by social media in June 2016. Within-country differences in infant feeding mode (‘any breastfeeding’ vs. ‘no breastfeeding’) were examined first before hierarchical multivariable logistic regression was used to determine if country differences in feeding mode persisted after adjusting for known factors associated with breastfeeding. Results In this sample, ‘any breastfeeding’ rates were 89, 71 and 72% in Australia, Ireland and the United Kingdom respectively. Within-country differences were evident in Australia, Ireland and the UK. Four factors showed no association with infant feeding mode in Australia while they did in the other countries (maternal age, income, skin-to-skin contact, support from friends and family). Two factors were unique to Australia: the odds of being in the ‘no breastfeeding’ group increased when the baby was delivered via caesarean and when not enough breastfeeding information was available after birth. One determinant was unique to Ireland: the odds of being in the ‘no breastfeeding’ group increased when respondents indicated they were not religious; in the UK this occurred when respondents were living in a town/village. After adjusting for sets of known factors of infant feeding mode based on socioecological and person-context models, country differences remained in hierarchical regressions: the odds of not breastfeeding were higher in both Ireland (AOR 3.3, 95%CI 1.8,6.1) and the United Kingdom (AOR 2.7, 95%CI 1.5, 4.7) compared to Australia. Conclusions This study indicates that different levels in the socioecological system are related to infant feeding behaviours. An adequate inter-systems level response would consider the interactions within and between behavioural and structural mechanisms which support breastfeeding behaviour. Optimising infant feeding practices will require an integrated web of interventions that go beyond the individual and focus on addressing factors that will influence families within their communities as they move between systems.