Modelling social readers: novel tools for addressing reception from online book reviews

Social reading sites offer an opportunity to capture a segment of readers’ responses to literature, while data-driven analysis of these responses can provide new critical insight into how people ‘read’. Posts discussing an individual book on the social reading site, Goodreads , are referred to as ‘reviews’, and consist of summaries, opinions, quotes or some mixture of these. Computationally modelling these reviews allows one to discover the non-professional discussion space about a work, including an aggregated summary of the work’s plot, an implicit sequencing of various subplots and readers’ impressions of main characters. We develop a pipeline of interlocking computational tools to extract a representation of this reader-generated shared narrative model. Using a corpus of reviews of five popular novels, we discover readers’ distillation of the novels’ main storylines and their sequencing, as well as the readers’ varying impressions of characters in the novel. In so doing, we make three important contributions to the study of infinite-vocabulary networks: (i) an automatically derived narrative network that includes meta-actants; (ii) a sequencing algorithm, REV2SEQ, that generates a consensus sequence of events based on partial trajectories aggregated from reviews, and (iii) an ‘impressions’ algorithm, SENT2IMP, that provides multi-modal insight into readers’ opinions of characters.

Spectrum graph-based de-novo sequencing algorithm MaxNovo achieves high peptide identification rates in collisional dissociation MS/MS spectra

We describe MaxNovo, a novel spectrum graph-based peptide de-novo sequencing algorithm integrated into the MaxQuant software. It identifies complete sequences of peptides as well as sequence tags that are incomplete at one or both of the peptide termini. MaxNovo searches for the highest-scoring path in a directed acyclic graph representing the MS/MS spectrum with peaks as nodes and edges as potential sequence constituents consisting of single amino acids or pairs. The raw score is a sum of node and edge weights, plus several reward scores, for instance, for complementary ions or protease compatibility. For search-engine identified peptides, it correlates well with the Andromeda search engine score. We use a particular score normalization and the score difference between the first and second-best solution to define a combined score that integrates all available information. To evaluate its performance, we use a human cell line dataset and take as ground truth all Andromeda-identified MS/MS spectra with an Andromeda score of at least 100. MaxNovo outperforms other software in particular in the high-sensitivity range of precision-coverage plots. We also identify incomplete sequence tags and study their statistical properties. Next, we apply MaxNovo to ion mobility-coupled time of flight data. Here we achieve excellent performance as well, except for potential swaps of the two amino acids closest to the C-terminus, which are not well resolved due to the low end of the mass range in MS/MS spectra in this dataset. We demonstrate the applicability of MaxNovo to palaeoproteomics samples with a Late Pleistocene hominin proteome dataset that was generated using three proteases. Interestingly, we did not use any machine learning in the construction of MaxNovo, but implemented expert domain knowledge directly in the definition of the score. Yet, it performs as good as or better than the leading deep learning-based algorithm.

Large-scale randomized experiments reveals that machine learning-based instruction helps people memorize more effectively

We perform a large-scale randomized controlled trial to evaluate the potential of machine learning-based instruction sequencing to improve memorization while allowing the learners the freedom to choose their review times. After controlling for the length and frequency of study, we find that learners for whom a machine learning algorithm determines which questions to include in their study sessions remember the content over ~69% longer. We also find that the sequencing algorithm has an effect on users’ engagement.

Feasibility of a Clinical Decision Support Tool to Manage Resistant Hypertension: Team-HTN, a Single-arm Pilot Study

ABSTRACT Introduction Based on defining criteria, hypertension (HTN) affects 31% to 46% of the adult U.S. population and almost 20% of service members. Resistant HTN (rHTN) consumes significant resources, carries substantial morbidity and mortality risk and costs over $350 billion dollars annually. For multiple reasons, only 48.3% of people with HTN are controlled, e.g., undiagnosed secondary HTN, therapeutic or diagnostic inertia, and patient adherence. Our purpose was to determine the feasibility of a web-based clinical decision support tool (CDST) using a renin-aldosterone system (RAS) classification matrix and drug sequencing algorithm to assist providers with the diagnosis and management of uncontrolled HTN (rHTN). Outcomes were blood pressure (BP) rates of control, provider management time, and end-user satisfaction. Methods This two-phase, prospective, non-randomized, single-arm, six-month pilot study was conducted in primary care clinics at a tertiary military medical center. Patients with uncontrolled HTN and primary care providers were recruited. Phase 1 patients checked their BP twice daily (AM and PM), three times weekly using a standardized arm cuff. Patients with rHTN were enrolled in phase 2. Phase 2 patients were managed virtually by providers using the CDST, the RAS classification matrix, and the drug sequencing algorithm which incorporated age, ethnicity, comorbidities, and renin/aldosterone levels. Medications were adjusted every 10 days until BP was at target, using virtual visits. Results In total, 54 patients and 16 providers were consented. One transplant patient was disqualified, 29 met phase 2 criteria for rHTN, and 6 providers completed the study. In phase 1, 45% (n = 24) of patients were identified as having apparent uncontrolled HTN using peak diurnal blood pressure (pdBP) home readings. In phase 2 (n = 29), previously undetected RAS abnormalities were identified in 69% (n = 20) of patients. Blood pressure control rates improved from 0% to 23%, 47%, and 58% at 2, 4, and 6 months, respectively. Provider management time was reduced by 17%. Using home pdBP readings identified masked HTN in almost 20% of patients that would have been missed by a single daily AM or PM home BP measurement. Feasibility and satisfaction trends were favorable. Conclusions Despite significant morbidity, mortality, and existing guidelines, over half of hypertensive patients are uncontrolled. Our results suggest that this CDST used with pdBP monitoring is a feasible option to facilitate improved rates of control in rHTN, aid in overcoming therapeutic/diagnostic inertia, improve identification of secondary HTN, and potentially, access. Further research with this tool in a larger population is recommended.

A hierarchical approach for solving an integrated packing and sequence-optimization problem in production of glued laminated timber

Integrated packing and sequence-optimization problems appear in many industrial applications. As an example of this type of problem, we consider the production of glued laminated timber (glulam) in sawmills: Wood beams must be packed into a sequence of pressing steps subject to packing constraints of the press and subject to sequencing constraints. In this paper, we present a three-stage approach for solving this hard optimization problem: Firstly, we identify alternative packings for small parts of an instance. Secondly, we choose an optimal subset of these packings by solving a set cover problem. Finally, we apply a sequencing algorithm in order to find an optimal order of the selected subsequences. For every level of the hierarchy, we present tailored algorithms, analyze their performance and illustrate the efficiency of the overall approach by a comprehensive numerical study.

Research on Construction and Application for the Model of Multistage Job Shop Scheduling Problem

Based on the practical application of an enterprise, we address the multistage job shop scheduling problem with several parallel machines in the first stage (production), a few parallel machines in the second stage (processing and assembly), and one machine in the following stages (including joint debugging, testing, inspection, and packaging). First, we establish the optimization objective model for the first two stages. Then, based on the design of the sequencing algorithm in the first two stages, a correction algorithm is designed between the first stage and the second stage to solve this problem systematically. Finally, we propose two benchmark approaches to verify the performance of our proposed algorithm. Verification of numerical experiments shows that the model and algorithm constructed in this paper effectively improve the production efficiency of the enterprise.

CONCURRENT CONCEPTUAL DESIGN SEQUENCING FOR MBSE OF COMPLEX SYSTEMS THROUGH DESIGN STRUCTURE MATRICES

Whilst Concurrent Conceptual Design (CCD) has been performed for many years at facilities such as: the Concurrent Design Facility at ESA and the Project Design Center at JPL-NASA, the sequencing know-how resides in their communities of practice. This paper strives to explain how a sequencing algorithm based on Design Structure Matrices can be used as an instrument to facilitate the interaction between disciplines during CCD studies for Model-Based systems exemplified with two case studies.