belongs to the medical industry, and temporal features include period of time, day of the week, whether the publishing date is an official holiday, and the development stage of epidemics. As the topical features are seldom investigated in similar studies, content features are also considered and represented by the topics involved in microblog entries.
First, in the category of publishers’ features, the publisher’s type is determined by the certification information and the name of the publisher. According to the Sina Weibo’s certification system, all of the certified
the time of Danmu comments sent by users is actually different ( Johnson, 2013 ). Pseudo-proximity captures the space dimension and has been further classified into spatial proximity and temporal proximity ( Fan et al. 2018 ). Spatial proximity refers to the physical closeness between the Danmu comment area and the focal area of the video section, whereas temporal proximity refers to the temporal closeness between the Danmu and the video ( Fan et al., 2018 ). Comment-content congruency reflects the support dimension and refers to the consistency between the content
Yukun Zheng, Yiqun Liu, Zhen Fan, Cheng Luo, Qingyao Ai, Min Zhang and Shaoping Ma
( Dupret & Piwowarski, 2008 ). Furthermore, Wang et al. (2015) looked into the revisiting behaviors of users in SERPs and incorporated non-sequential behaviors into the PSCM. Liu et al. (2017) proposed the time-aware click model (TACM), which can better capture the temporal information.
2.2 Document Ranking
A lot of learning-to-rank approaches have been proposed to address document ranking problem, such as RankNet ( Burges et al., 2005 ), RankBoost ( Freund et al., 2003 ), and LambdaMART (Wu, Burges, Svore, & Gao, 2010). All these learning-to-rank algorithms
Research and Development in Information Retrieval 595 602 10.1145/1390334.1390436
Efron, M., Lin, J. J., He, J., & de Vries, A. P. (2014). Temporal feedback for tweet search with non-parametric density estimation. International Conference on Research and Development in Information Retrieval , 33–42. Efron M. Lin J. J. He J. de Vries A. P. 2014 Temporal feedback for tweet search with non-parametric density estimation International Conference on Research and Development in Information Retrieval 33 42
Ghosh, S., & Desarkar, M. S. (2018). Class specific TF-IDF boosting
media are at the centre of most activities within organizations. Affordance lens on macro-level concerning with knowledge sharing and coordination and on microlevel with decision-making and temporal orientation are poised to be shaped by the use of social media at work ( Leonardi & Vaast, 2017 ).
Thus, we argue that the use of social media within organizations will affect individuals, groups, and organizational processes and enhance information sharing behaviour. Despite the prior research in which the connection of individual discussed in terms of blogs ( Wattal
Nowadays, we can use the Resource Description Framework (RDF) ( Klyne, Carroll, & McBride, 2004 ), which is recommended by the World Wide Web Consortium (W3C) as the foundation of the Semantic Web, to restore the knowledge. An RDF statement is a triple presented as 〈 subject , predicate , object 〉, which describes a property value of a subject or the relation between the two entities – the subject and the object . In practice, a huge amount of entities and statements contains spatial and temporal information, e.g., a city is always
, especially the developed Linked Data technology, however, will help improve the current situation.
In recent years, ontology-based semantic technology has been utilized to refactor genealogy data formatting abroad. Successful examples are “FamilySearch.org” by the Genealogical Society of Utah (GSU) and “ancestry.com”, which not only provide a keyword search function that describes document features but also enable users to explore a genealogy resource and its member relationships by featuring contents such as temporal-spatial correlation and kinship. One innovative case
Will R. Thomas, Benjamin Galewsky, Sandeep Puthanveetil Satheesan, Gregory Jansen, Richard Marciano, Shannon Bradley, Jong Lee, Luigi Marini and Kenton McHenry
described in more detail below).
We must weave together a number of concepts and methods from the literature to incrementally build an annotated corpus from archival records. These concepts are as follows:
–– treebank corpus annotation
–– relational lenses
–– document interpretation acts
–– weak supervised learning
–– convolutional neural networks
–– long short-term memory
–– bidirectional long short-term memory
–– multimodal long short-term memory
–– connectionist temporal classifier
We can start with treebank corpus annotation
. Martinez-Budria, E., Armas, R.D., Ibanez, M.N. and Mesa, R.(1999), A study of the efficiency of Spanish port authorities using Data Envelopment Analysis. International Journal of Transport Economics 26(2): 237-253.
23. Min, H. and Park, B.I. (2005), Evaluating the inter-temporal efficiency trends of international container terminals using data envelopment analysis. International Journal of Integrated Supply Management 1(3): 258-277.
24. Munisamy, S. and Singh, G. (2011), Benchmarking the efficiency of Asian container ports, African journal of business
et al. (2014) .
As mentioned before, it is not mandatory for users to log in the OPAC with personal account, which leads to the less data which can be used for analysis. Therefore, the device transitions between the phones and tablets are much less in our work.
4.2 Temporal Characteristics of Cross-device Transition
Temporal characteristics are always an important perspective in the research about user’s information-seeking behavior. In this section, we introduced the basic temporal characteristics about the device transition in OPAC, such as the hour when