Browsing by Author "Abera, Bekele"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Event Modeling from Amharic News Articles
    (Addis Ababa University, 2018-02-04) Abera, Bekele; Getahun, Fekade (PhD)
    With the increase of online information overload available to us, everyday tasks such as extracting, searching, understanding and relating relevant data have become intractable. A large percentage of these information are discussing past, current, and future real world events. Events are dynamic data structures that play a key role in understanding phenomena happing in real world, which are basically driven by the four ‘W’s’ (what, who, when, and where). This natural progression of questions is a classic example of what one might ask about an event. This results in natural way to explain complicated relations between people, places, actions and objects. Event centered modeling captures the dynamic aspects of an event along with semantic representation of event facts. In this research work, we have proposed and developed event extraction and representation model from Amharic news article. Event modeling involves key event identification, event elements extraction, and event semantic elements representation. Event triggers tells the action taking place in news article. To identify the mention of event in news article we used manually collected event trigger words and phrases from various news domains. For event elements extraction, we used named entity recognizer and other local features like potential trigger, event extent, path from the extent to head word of the trigger. Machine learning Maximum entropy classifier is trained using event related news article collected from Fana Broadcast Corporate news archive. For event representation, we designed ontology based event representation model that provides deeper semantic through event information representation. A prototype showing an event extraction and representation is developed using different programming environment. Evaluation of trigger identification and event elements extraction is carried out by comparing manually tagged news article with the automatically extracted event information by the system. The evaluation result shows that the trigger identifier module obtain precision (67.1%) of event correctly which contributes to the better event elements extraction. The event elements extractor component shows greater obtaining precision (69.1%) while event classification module classify about (72%) of event correctly. The representative ability of our event representation model is evaluated with respect to requirements and event dimensions we covered in this work.
  • No Thumbnail Available
    Item
    Event Modeling from Amharic News Articles
    (Addis Ababa University, 2/4/2018) Abera, Bekele; Getahun, Fekade (PhD)
    With the increase of online information overload available to us, everyday tasks such as extracting, searching, understanding and relating relevant data have become intractable. A large percentage of these information are discussing past, current, and future real world events. Events are dynamic data structures that play a key role in understanding phenomena happing in real world, which are basically driven by the four ‘W’s’ (what, who, when, and where). This natural progression of questions is a classic example of what one might ask about an event. This results in natural way to explain complicated relations between people, places, actions and objects. Event centered modeling captures the dynamic aspects of an event along with semantic representation of event facts. In this research work, we have proposed and developed event extraction and representation model from Amharic news article. Event modeling involves key event identification, event elements extraction, and event semantic elements representation. Event triggers tells the action taking place in news article. To identify the mention of event in news article we used manually collected event trigger words and phrases from various news domains. For event elements extraction, we used named entity recognizer and other local features like potential trigger, event extent, path from the extent to head word of the trigger. Machine learning Maximum entropy classifier is trained using event related news article collected from Fana Broadcast Corporate news archive. For event representation, we designed ontology based event representation model that provides deeper semantic through event information representation. A prototype showing an event extraction and representation is developed using different programming environment. Evaluation of trigger identification and event elements extraction is carried out by comparing manually tagged news article with the automatically extracted event information by the system. The evaluation result shows that the trigger identifier module obtain precision (67.1%) of event correctly which contributes to the better event elements extraction. The event elements extractor component shows greater obtaining precision (69.1%) while event classification module classify about (72%) of event correctly. The representative ability of our event representation model is evaluated with respect to requirements and event dimensions we covered in this work.
  • No Thumbnail Available
    Item
    Influence of Attitude on Mobile Banking Adoption: The Case of Dashen and United Banks in Addis Ababa
    (Addis Ababa University, 2019-06) Abera, Bekele; Workneh, Kassa (PhD)
    The aim of this study was to assess the influence of attitude on mobile banking adoption in Ethiopia: the case of Dashen and United banks in Addis Ababa. In so doing, factors influencing attitude toward mobile banking and the influence of attitude and its corresponding strength on intention to adopt mobile banking were assessed. In addition to these primary objectives, assessing the significance of variations in socio-demographic variables on attitude and intention to adopt mobile technology was part of this study. Descriptive and causal research design was employed. Stratified sampling method was used to collect quantitative and qualitative data from individuals who subscribed for mobile banking service of Dashen Bank and United Bank i.e. Amole and Hibir respectively. Accordingly, 394 usable questionnaires were obtained and used for further analysis. SPSS version 21 was used to analyze the collected data. The collected data were analyzed using central tendency (median), measure of dispersion (standard deviation), independent sample T-test, ANOVA, correlation & regression analysis. Interviews were conducted with subscribers with different mobile banking usage frequency. To develop the models used for analysis, inputs from TAM, ToT, trust and the concept of attitude strength was used. The results of the analysis indicate that among the socio-demographic factors included in this study occupation, mobile banking usage status and usage frequency significantly influence both attitude and intention while monthly income and service provider significantly influence intention only. The regression outputs indicate that the factors that influence attitude toward mobile banking are perceived usefulness, perceived ease of use and trust. Similarly, attitude toward success, attitude toward process/learning and attitude strength significantly influence intention to adopt mobile banking while attitude toward failure had an insignificant influence on intention. Based on the findings, the researcher forwarded recommendations to enhance mobile banking adoption. These are improving reliability, awareness creation, emphasize on making mobile banking easier and trustworthy, and creating a situation which necessitates the need to use mobile banking.