Context-aware Service Input Ranking by Learning from Historical Information

Abstract

Users visit on-line services and compose them to accomplish on-line tasks, such as shopping on-line. Quite often, users enter the same information into various on-line services to finish on-line tasks. However, repetitively typing the same information into web forms is a tedious job for users. In this paper, we propose a context-aware ranking framework to rank values for input parameters. We propose 6 categories of ranking features constructed from various types of information, such as user contexts and patterns of user inputs. Our framework adopts learning-to-rank (LtR) algorithms that consist of a set of machine learned models to automatically construct ranking models by integrating the ranking features. When a user enters a value to an input parameter, an interaction between the user input and the input parameter is established. Our framework learns information relevant to such interactions and ranks user inputs in different contexts. Through empirical studies on the real-world on-line services, we obtain the following main results: (1) Among the 8 state-of-the-art learning-to-rank models, RankBoost can outperform other LtR models on ranking user inputs for input parameters; (2) Our framework using IRSVM that performs the worst among the LtR models outperforms the two baseline conventional ranking models and Google Chrome Autofilling, an industrial tool, on ranking user inputs to input parameters; and (3) We observe that the textual information of user inputs and input parameters is the most influential factor on ranking user inputs. Among the various types of contextual data, user locations and time matter the most to the ranking of user inputs.

A Machine Learning Approach for Automated Filling of Categorical Fields in Data Entry Forms

“…Data entry forms are essential software user interface (UI) elements [41,67] to collect users' inputs. According to statistics, approximately 70 million professionals or 59% of all professionals in the United States need to complete on-line forms for their daily jobs [76]. However, form filling is time-consuming and error-prone [63].…”

“…Some form filling tools [31,76] support filling categorical fields, by suggesting frequently selected values in a field or values selected by a user in some similar fields from 3rd-party software systems. Nevertheless, they provide limited support due to the low accuracy of their suggestions; moreover, their usage may violate enterprise security policies, since they rely on information from 3rd-party software systems [78].…”

Supervised machine learning for classification mining and ranking of illegal web contents = Aprendizaje automático supervisado para la clasificación, extracción de conocimiento y ordenación de contenidos web ilegales

“…The reader can notice that the values of k are not equally sampled, that we selected five values between zero and 10, while the other five values are greater than 10. This distribution is because having the head of a ranked list sorted correctly is more important than its tail (Cao et al, 2006;Wang et al, 2017c). The superiority of the listwise approach is evidence of its suitability among the other methods (see Figure 5.12).…”

“…Agichtein et al (2006) employed RankNet algorithm to leverage search engine results by incorporating user behavior. Wang et al (2017c) presented LtR-based framework to rank input parameters values of online forms. They used six categories of features extracted from user contexts and patterns of user inputs.…”

“…To learn an optimal order of the onion domains through their descriptors, we adopt a Learning to Rank (LtR) approach adapted from the Information Retrieval (IR) field. In a traditional IR problem, a training sample is a vector of three components: the relevance judgment, which can be binary (Wang et al, 2017c) or with multiple levels of relevance (Li, 2011a), the query ID, and the feature vector that describes the ranked instance.…”