Modelling the Latent Semantics of Diffusion Sources in Information Cascade Prediction

Predicting the information spread tendency can help products recommendation and public opinion management. The existing information cascade prediction models are devoted to extract the chronological features from diffusion sequences but treat the diffusion sources as ordinary users. Diffusion source, the first user in the information cascade, can indicate the latent topic and diffusion pattern of an information item to mine user potential common interests, which facilitates information cascade prediction. In this paper, for modelling the abundant implicit semantics of diffusion sources in information cascade prediction, we propose a Diffusion Source latent Semantics-Fused cascade prediction framework, named DSSF. Specifically, we firstly apply diffusion sources embedding to model the special role of the source users. To learn the latent interaction between users and diffusion sources, we proposed a co-attention-based fusion gate which fuses the diffusion sources’ latent semantics with user embedding. To address the challenge that the distribution of diffusion sources is long-tailed, we develop an adversarial training framework to transfer the semantics knowledge from head to tail sources. Finally, we conduct experiments on real-world datasets, and the results show that modelling the diffusion sources can significantly improve the prediction performance. Besides, this improvement is limited for the cascades from tail sources, and the adversarial framework can help.

Recall and Understanding of Discharge Information in Observation Ward Patients: An Explorative Observational Study

Effective communication is essential for understanding and recall of hospital discharge information. This study aimed to explore discharge information, patient recall and patient involvement in discharge encounters. We conducted an explorative observational study at a secondary care level, observational ward. Patients discharged to their home were asked to participate. 34 patients were assessed for eligibility, of which 13 were included in the analysis. Multiple sources of data were collected: videotapes of discharge encounters, questionnaires to patients and physicians, and semi-structured interviews with patients 2 weeks after discharge. All patients were satisfied with the information received. Five of the eight patients discharged with more than one change in medication had only partial or no recall of these changes. In seven of the 13 encounters the patients and physicians did not agree on the main message most important information item. The patients were to a small extent involved in decision-making. Our findings highlight the gaps in the information exchange at discharge encounters and the resulting poor information recall among patients. Patients do not seem aware of these gaps. Greater provider awareness of patient involvement in the encounter and inclusion of the patient’s perspective may improve communication, and consequently understanding and recall.

Evaluating the Psychometric Properties of the Short Dark Triad (SD3) in Italian Adults and Adolescents

The term Dark Triad refers to three socially aversive personality dimensions (i.e., Machiavellianism, narcissism, and psychopathy) that are evident in the normal range of personality. Jones and Paulhus (2014) developed the Short Dark Triad (SD3) as a 27-item measure of the three constructs. To assess the psychometric properties of the Italian translation, 678 adult university students and 442 adolescent high school students were sampled. Cronbach’s α values for the subscales were acceptable in both samples. Subscale intercorrelations ranged from .29 to .55 in adults and .29 to .53 in adolescents. Although subscale means were higher in the adolescent sample, the two item correlation matrices did not differ significantly. A confirmatory factor analysis using multidimensional full-information item response theory showed that a three-correlated-factor model provided the best fit in both adults and adolescents. When controlled for overlap, SD3 subscales showed adequate convergent and discriminant validity coefficients in both samples. The current research contributes to the literature on dark personalities in two ways: (a) It provides detailed psychometric support for the Italian translation of SD3 and (b) it directly compares SD3 performance in younger and older students.

Supervised Convolutional Matrix Factorization for Document Recommendation

Recently, document recommendation has become a very hot research area in online services. Since rating information is usually sparse with exploding growth of the numbers of users and items, conventional collaborative filtering-based methods degrade significantly in recommendation performance. To address this sparseness problem, auxiliary information such as item content information may be utilized. Convolution matrix factorization (ConvMF) is an appealing method, which tightly combines the rating and item content information. Although ConvMF captures contextual information of item content by utilizing convolutional neural network (CNN), the latent representation may not be effective when the rating information is very sparse. To address this problem, we generalize recent advances in supervised CNN and propose a novel recommendation model called supervised convolution matrix factorization (Super-ConvMF), which effectively combines the rating information, item content information and tag information into a unified recommendation framework. Experiments on three real-world datasets, two datasets come from MovieLens and the other one is from Amazon, show our model outperforms the state-of-the-art competitors in terms of the whole range of sparseness.

Aplikasi Pembuat Spesifikasi Komputer Berbasis Web

INTISASIAplikasi pembuat spesifikasi komputer berbasis web merupakan bagian dari E-Commerce yang sangat membantu pengambilan keputusan bagi user dalam pembelian komputer. Dengan aplikasi ini pelanggan dengan mudah dapat menentukan spesifikasi komputer yang diinginkan sesuai dengan anggaran yang dimiliki. Pelanggan juga bisa menentukan komponen-komponen apa saja yang ingin dirakit dilengkapi informasi harga masing-masing item dan nantinya total keseluruhan komponen yang dipilih menjadi report yang dapat disajikan layanan ini. Kelebihan budget harga dapat dengan mudah teratasi dengan memilih kembali komponen dengan nominal harga yang lebih murah. Bagi pelanggan yang belum paham mengenai spesifikasi komponen komputer juga sangat terbantu dengan adanya aplikasi ini, sebab aplikasi ini akan memberi report peringatan jika dalam menentukkan pilihan komponen tidak compatible dengan peripheral yang telah dipilih sebelumnya. Sisi lain dari layanan ini bisa menjadi media konsultan digital dalam menentukan spesifikasi komputer yang diinginkan sesuai dengan biaya dengan anggaran yang dimiliki oleh konsumen.Kata kunci— Teknologi informasi, internet, web. ABSTRACTApplication computer specification maker web based is part of E-Commerce which is very helpful for decision making in the purchase of computer users. With this application the customer can easily determine the desired specifications of the computer in accordance with the budget they own. Be customers also can determine what components which want to assembled by equipped of each price information item and continously the total components which selected will be a report that can be presented with this service.Excess budget prices can be easily solved by selecting the component with a nominal return a cheaper price. For the customers who do not understand about the specifications of the computer components are also very helpful with this application, because this application will give the report a warning if in determining choice of components is not compatible with peripherals that have been previously selected.The other side of this service can be a digital media consultant in determining the desired specifications of the computer in accordance with the cost to the budget which is owned by the consumer.Kata kunci— Information technology, internet, web.

Multidimensionality evaluation of supply chain management integration

Integration is constantly reported in the literature as an essential feature of SCM. However, it is as difficult to define as to operationalize it, resulting in a lack of information on how to increase the level of integration among members. Thus, this research aims to evaluate the dimensionality of SCI, to check alignment with the features identified in the literature using multivariate statistical analysis. The methodology used was based on a questionnaire to assess the level of companies integration with suppliers of its supply chain. This instrument consisted of 21 items, with response options: yes, no or not applicable. The questions focused on evaluating the integration with suppliers, so each company consulted could answer a questionnaire for each supplier, since the intensity of relationships varies. Thus, 41 companies participated in the survey, resulting in 205 responses. Full-information item factor analysis and principal component analysis on the correlation matrix tetrachoric were used for the instrument dimensionality analysis. They are appropriate procedures for analysis of dichotomous variables. The results of this analysis enabled grouping the questionnaire items in the following underlying factors: trust, information sharing, partnership, collaboration or cooperation, and coordination. The identification of such factors such as dimensions of SCI enables greater understanding on how to raise the level of integration among the members of a supply chain.

The User-Subjective Approach

This chapter suggests a new design approach developed specifically for PIM systems. It argues that PIM is unique in that the person who curates the information is the same person who later retrieves it. The user-subjective approach takes advantage of this unique feature and suggests that PIM systems should make systematic use of subjective (user-dependent) attributes. The approach identifies three specific subjective attributes – the importance of the information item to the user, the project to which it belongs, and the context in which the item is used, and suggests three design principles, one for each subjective attribute.