Current Issue
    , Volume 1 Issue 5 Previous Issue    Next Issue
    For Selected: View Abstracts Toggle Thumbnails
    Orginal Article
    Impacts of Time Constraint on Information Behaviors in Pedestrian Navigation
    Wu Dan,Li Yi,Dong Jing
    2017, 1 (5): 2-11.  DOI: 10.11925/infotech.2096-3467.2017.05.02
    Abstract   HTML ( 5 PDF(431KB) ( 139 )  

    [Objective] This paper investigates the impacts of time constraint on users’ information behaviors in pedestrian navigation and their interaction experiences. [Methods] We recruited 20 college students and randomly divided them into two groups (with and without time constraint) for the pedestrian navigation experiment. These participants completed two different types of tasks: Outdoor and Indoor Pedestrian Navigations. [Results] We found that time constraint induced some feeling of stress. However, there was no significant difference among the strength of time pressure. Once the users did not know their destination and its exact location, the time constraint posed significant impacts to task duration, time spent on text page and the number of slides on the screen. When users knew their destination but did not know its specific location, the time constraint has no significant impact on users’ information behaviors. For indoor navigation, users’ zooming and sliding activities were significantly influenced by time constraint. [Limitations] The number of participants in our experiment is small. [Conclusions] Time constraint affects the information behaviors of pedestrian navigation system users. With time constraint, they could reach the destination quickly by reducing screen operations.

    Figures and Tables | References | Supplementary Material | Related Articles | Metrics
    Route Planning in Pedestrian-Map APP Interactions
    Wu Dan,Cheng Lei
    2017, 1 (5): 12-22.  DOI: 10.11925/infotech.2096-3467.2017.05.03
    Abstract   HTML ( 1 PDF(1542KB) ( 195 )  

    [Objective] This paper constructs a model for route planning based on the impacts of different contexts on pedestrian’s walking behaviors. [Methods] First, we collected data from 30 participants of an outdoor pedestrian navigation experiment. Then, we analyzed the ties between contexts and users’ behaviors with correlation and regression tests. [Results] At the initial planning stage, more destinations chosen by the pedestrians meant longer searching time, while more users’ attention to the estimated time led to longer browsing time. User’s subjective time pressure, system location and destination choice also affected their attention to estimated time. In the re-planning stage, different genders and ages had different subjective time pressures on the users. The more difficult tasks generated fewer operations. [Limitations] There were some subjective issues with the data processing. The changing of user’s psychology and behaviors may also influence the results. [Conclusions] The proposed model focuses on the user factors and reveals the relationship among the contexts of the initial plannings and the re-routings, which provide valuable information to the mobile map developers.

    Figures and Tables | References | Supplementary Material | Related Articles | Metrics
    Navigation Awareness of Pedestrian Using Think-Aloud Method
    Wu Dan,Lu Liuxing
    2017, 1 (5): 23-31.  DOI: 10.11925/infotech.2096-3467.2017.05.04
    Abstract   HTML ( 2 PDF(745KB) ( 220 )  

    [Objective] This paper studies the pedestrian’s changing awareness, aiming to use the think-aloud method to analyze the navigational information behaviors. It also provides suggestions to mobile map development from the users’ perspectives. [Methods] We designed three pedestrian navigation experiments in the real outdoor environment, and required the participants use the map APP while thinking loud out. [Results] We found that users paid more attention to the search features than to the external information of the pedestrian navigation system. People paid attention to the display of search results, and their main awareness changed from ambient temperature to location, and finally to destination situation. [Limitations] We classified the data with three time slots manually, which might generate some errors. [Conclusions] Think-Aloud method can be applied to investigate user-APP interactions in the real outdoor environment, which help us optimize the map APP to improve user experience.

    Figures and Tables | References | Supplementary Material | Related Articles | Metrics
    Studying User Distractions with GPS Based Pedestrian Navigation System
    Wu Dan,Yuan Fang
    2017, 1 (5): 32-41.  DOI: 10.11925/infotech.2096-3467.2017.05.05
    Abstract   HTML ( 2 PDF(995KB) ( 1030 )  

    [Objective] The purpose of this paper is to reduce user distractions effectively by analyzing their reactions to various positioning accuracy of a pedestrian navigation system. [Methods] First, we collected users’ behavior data from the simulation and controlled experiments. Then, we compared the user distraction frequencies and durations with descriptive statistics and significance tests. [Results] We found that users paid more attention to the orientation of the GPS, which increased the number of stopovers and reduced interactions with the APP. [Limitations] We could not exclude the influence of the individual factors on the results and few previous studies discussed the theoretical foundation of our study. [Conclusions] To reduce distractions, pedestrians should decrease their reliance on the navigation system, while the latter needs to provide more specific and comprehensive information.

    Figures and Tables | References | Supplementary Material | Related Articles | Metrics
    Changing Sentiments of Pedestrian Navigation System Users
    Wu Dan,Liu Chang,Li Yi
    2017, 1 (5): 42-51.  DOI: 10.11925/infotech.2096-3467.2017.05.06
    Abstract   HTML ( 1 PDF(1725KB) ( 259 )  

    [Objective] This paper aims to optimize user experience and keep them using the pedestrian navigation system. [Methods] First, we collected data from an experiment with 30 participants. Then we conducted analysis with the help of sentiment dictionaries. Finally, we obtained influencing factors and their changing patterns with the number of degree adverbs, Chinese sentiment vocabulary Ontology and degree-calculating formula of polar phrases. [Results] We found that users’ sentiment changed due to the systematic and environmental factors. Untimely system updates, inaccurate locations and tough environment all posed negative effects to the user’s sentiments. [Limitations] Text analysis could not study the sentiments comprehensively. [Conclusions] We could optimize user experience by improving system design and adding user-friendly features, which provides direction for future developments.

    Figures and Tables | References | Supplementary Material | Related Articles | Metrics
    Information Consumption of Urban Chinese Residents: An Empirical Study Based on Dynamic Spatial Durbin Panel Model
    Zhang Su
    2017, 1 (5): 52-61.  DOI: 10.11925/infotech.2096-3467.2017.05.07
    Abstract   HTML ( 2 PDF(648KB) ( 306 )  

    [Objective] This paper analyzes the factors influencing information consumption, aiming to further promote such activities among urban Chinese residents. [Methods] First, we studied the development condition, spatial correlation and three types of internal and external influencing factors. Then, we constructed the corresponding Dynamic Spatial Durbin Panel Model and conducted an empirical study. [Results] The information consumption had the durable features but posed no spillover effects. The urban residents’ consumption could also affect the adjoining region residents’ behaviors. The increasing of price and income promoted the information consumption in short term. The improvement of education and information infrastructure posed spatial spillover effects to adjoining residents. In the long term, only the price and income had impacts on local residents. [Limitations] We only examined the impacts of the price, education level, information infrastructure, number of cyber citizen, and income. Other factors might also affect the results. [Conclusions] We must study the residents’ information consumption behaviors based on all spatial spillovers to avoid biased results.

    Figures and Tables | References | Related Articles | Metrics
    Automatically Segmenting Middle Ancient Chinese Words with CRFs
    Wang Xiaoyu,Li Bin
    2017, 1 (5): 62-70.  DOI: 10.11925/infotech.2096-3467.2017.05.08
    Abstract   HTML ( 5 PDF(477KB) ( 159 )  

    [Objective] The purpose of this paper is to explore the influence of the word segmentation consistency and the corpus types in Middle Ancient Chinese (MAC). It tries to improve the accuracy and efficiency of the automatic word segmentation, a basic procedure in processing ancient Chinese, based on the CRFs model. [Methods] First, we optimized the segmentation principles for MAC historical records, Buddhist scriptures and novels. Then, we combined the CRFs model with dictionary to reduce the segmentation inconsistency in the manual procedures. Finally, we added two features to the CRFs model (i.e. character classification and dictionary information), and identified the best word segmentation template by comparison experiments. [Results] The F-score was higher than 99% in the closed test, while it was from 89% to 95% in the open test. [Limitations] The segmentation consistency was improved on the words with two characters, and more studies were needed on the segmentation of words with more than three characters. [Conclusions] The proposed method could effectively improve the accuracy of automatic word segmentation for mediaeval Chinese corpus.

    Figures and Tables | References | Supplementary Material | Related Articles | Metrics
    Classifying Sentiments Based on BPSO Random Subspace
    Zhang Qingqing,Liu Xilin
    2017, 1 (5): 71-81.  DOI: 10.11925/infotech.2096-3467.2017.05.09
    Abstract   HTML ( 1 PDF(1107KB) ( 277 )  

    [Objective] This paper aims to solve the issue of representing high dimensional features in Chinese sentiment analysis, with the help of RS_BPSO, a selective ensemble algorithm. [Methods] First, we developed the framework and algorithm of the proposed RS_BPSO model based on the theory of Random Subspace and Binary Particle Optimization. Then, we transformed the Chinese review corpus into structured feature vectors and examined the new model. [Results] We found that the diversity and accuracy of the RS_BPSO model better than the standard RS model. [Limitations] We did not run the proposed model with corpus in foreign languages. [Conclusions] The RS_BPSO model could be an effective method to classify Chinese sentiments.

    Figures and Tables | References | Related Articles | Metrics
    Collecting Mobile Data Based on Content Awareness——An Empirical Study
    Xia Lixin,Yang Jinqing,Cheng Xiufeng
    2017, 1 (5): 82-93.  DOI: 10.11925/infotech.2096-3467.2017.05.10
    Abstract   HTML ( 3 PDF(2871KB) ( 157 )  

    [Objective] This paper proposes the framework for a mobile data retrieval and analysis system based on context-awareness, aiming to optimize the related data mining procedures. [Context] Nowadays, the automatic dynamic and comprehensive applications for mobile data mining were still being developed. [Methods] First, we proposed a framework to collect mobile data from the client side with the help of Android AWARE sensor. The collected data was received by the server automatically. Then, we designed an empirical study to analyze the retrieved APP usage data. [Results] The proposed system could effectively recommand useful APPs to the mobile users. [Limitations] More in-depth analysis was needed to examine the collected data. [Conclusions] The proposed framework could help us effectly retrieve and analyze mobile useage data, which benefits the contextual computing research and the mobile informaiton behavior studies.

    Figures and Tables | References | Related Articles | Metrics
    Personalized Recommendation Algorithm of Multi-faceted Trust Tensor Based on Tag Clustering
    Chen Meimei,Xue Kangjie
    2017, 1 (5): 94-101.  DOI: 10.11925/infotech.2096-3467.2017.05.11
    Abstract   HTML ( 1 PDF(1014KB) ( 153 )  

    [Objective] This paper aims to solve the low accuracy issue facing personalized recommendation algorithm of multi-faceted trust tensor based on tag clustering. [Methods] First, we proposed a new method to calculate multi-faceted trust based on tag clusters. Then, we introduced the TF-IDF and Pearson similarity to indicate strength of inter-cluster and intra-cluster trust. Finally, we built recommendation mechanism based on tensor decomposition to reflect the trust intensity from different facets. [Results] We examined the new algorithm with the Last.fm dataset. The precision, recall and F1 measures were better than traditional methods. Among them, the F1 measure was increased by 2.29% on average. [Limitations] Our new algorithm needs to be examined with datasets from Weibo or Twitter. [Conclusions] The proposed algorithm could effectively increase the accuracy of recommendation by defining and quantifying trust relationship among users. It improves the user experience of social network systems.

    Figures and Tables | References | Related Articles | Metrics
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626,82624938   E-mail:jishu@mail.las.ac.cn