<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.4 20241031//EN"
        "https://jats.nlm.nih.gov/publishing/1.4/JATS-journalpublishing1-4.dtd">
<article  article-type="research-article"        dtd-version="1.4">
            <front>

                <journal-meta>
                                                                <journal-id>veri bilim derg</journal-id>
            <journal-title-group>
                                                                                    <journal-title>Veri Bilimi</journal-title>
            </journal-title-group>
                                        <issn pub-type="epub">2667-582X</issn>
                                                                                            <publisher>
                    <publisher-name>Murat GÖK</publisher-name>
                </publisher>
                    </journal-meta>
                <article-meta>
                                        <article-id/>
                                                                <article-categories>
                                            <subj-group  xml:lang="en">
                                                            <subject>Engineering</subject>
                                                    </subj-group>
                                            <subj-group  xml:lang="tr">
                                                            <subject>Mühendislik</subject>
                                                    </subj-group>
                                    </article-categories>
                                                                                                                                                        <title-group>
                                                                                                                        <trans-title-group xml:lang="en">
                                    <trans-title>Automatic Question Identification on Turkish Tweets</trans-title>
                                </trans-title-group>
                                                                                                                                                                                                <article-title>Türkçe Tweetler Üzerinde Otomatik Soru Tespiti</article-title>
                                                                                                    </title-group>
            
                                                    <contrib-group content-type="authors">
                                                                        <contrib contrib-type="author">
                                                                <name>
                                    <surname>Mayda</surname>
                                    <given-names>İslam</given-names>
                                </name>
                                                                    <aff>YILDIZ TEKNİK ÜNİVERSİTESİ</aff>
                                                            </contrib>
                                                                                </contrib-group>
                        
                                        <pub-date pub-type="pub" iso-8601-date="20181225">
                    <day>12</day>
                    <month>25</month>
                    <year>2018</year>
                </pub-date>
                                        <volume>1</volume>
                                        <issue>1</issue>
                                        <fpage>1</fpage>
                                        <lpage>6</lpage>
                        
                        <history>
                                    <date date-type="received" iso-8601-date="20181129">
                        <day>11</day>
                        <month>29</month>
                        <year>2018</year>
                    </date>
                                                    <date date-type="accepted" iso-8601-date="20181224">
                        <day>12</day>
                        <month>24</month>
                        <year>2018</year>
                    </date>
                            </history>
                                        <permissions>
                    <copyright-statement>Copyright © 2018, Veri Bilimi</copyright-statement>
                    <copyright-year>2018</copyright-year>
                    <copyright-holder>Veri Bilimi</copyright-holder>
                </permissions>
            
                                                                                                <trans-abstract xml:lang="en">
                            <p>In this work, it was tried to identify which areincludes question from the tweets written in Turkish shared in Twitter, with arule-based approach. As a data set, tweets that are shared with a certainhashtag are used instead of randomly sampled tweets. The reason for this, it isaimed to identify the questions asked for a specific focus in this study. Forthe experiments, 354 tweets were collected, shared with the hashtag that wascreated in order to contribute of the audience to the program by asking thequestions while a historical topic was being spoken in the program broadcastlive on a television channel. The Zemberek library has been used to fix typosin these tweets. Then, according to the Turkish question sentence structure, 3simple rules are defined aiming at keeping the precision value or thesensitivity value high and each one is applied as a separate method. As aresult of experiments, 100% precision, 96.48% sensitivity and 0.929 F-scorevalues were recorded as the most successful performances.</p></trans-abstract>
                                                                                                                                    <abstract><p>Bu çalışmada Twitter&#039;da paylaşılan Türkçe yazılmış tweetlerden, içindesoru geçenleri kural tabanlı yaklaşımla tespit edilmeye çalışılmıştır. Veriseti olarak rastgele örneklenen tweetler yerine belirli bir etiket ilepaylaşılan tweetler kullanılmıştır. Bunun sebebi, bu çalışmada belirli birodağa yönelik sorulan soruların tespitinin amaçlanmış olmasıdır. Deneyler için,bir televizyon kanalında canlı olarak yayınlanan programda tarihi bir konukonuşulurken izleyicilerin sorularıyla programa katkıda bulunması amacıylaaçılan etiketle paylaşılan 354 tweet toplanmıştır. Bu tweetlerdeki yazımhatalarını düzeltmede Zemberek kütüphanesinden yararlanılmıştır. Daha sonraTürkçe soru cümlesi yapısına göre, kesinlik değerini veya duyarlılık değeriniyüksek tutmayı amaçlayan 3 farklı basit kural tanımlanmış ve her biri ayrıyöntem olarak deneylerde uygulanmıştır. Deneyler sonucunda %100 kesinlik,%96,48 duyarlılık ve 0.929 F-skoru değerleri en başarılı performanslar olarakkaydedilmiştir.</p></abstract>
                                                            
            
                                                                                        <kwd-group>
                                                    <kwd>Twitter</kwd>
                                                    <kwd>  Türkçe tweetler</kwd>
                                                    <kwd>  Soru tespiti</kwd>
                                            </kwd-group>
                            
                                                <kwd-group xml:lang="en">
                                                    <kwd>Twitte</kwd>
                                                    <kwd>  Turkish tweets</kwd>
                                                    <kwd>  Question identification</kwd>
                                            </kwd-group>
                                                                                                                                        </article-meta>
    </front>
    <back>
                            <ref-list>
                                    <ref id="ref1">
                        <label>1</label>
                        <mixed-citation publication-type="journal">Statista, “Number of monthly active Twitter users worldwide from 1st quarter 2010 to 3rd quarter 2017 (in millions)” www.statista.com. [Online]. Available: https://www.statista.com/statistics/282087/number-of-monthly-active-twitter-users/, 2017.</mixed-citation>
                    </ref>
                                    <ref id="ref2">
                        <label>2</label>
                        <mixed-citation publication-type="journal">M. Efron ve M. Winget, “Questions are content: a taxonomy of questions in a microblogging environment”, Proc. of ASIST ’10, 2010.</mixed-citation>
                    </ref>
                                    <ref id="ref3">
                        <label>3</label>
                        <mixed-citation publication-type="journal">B. Li, X. Si, M. R. Lyu, I. King ve E. Y. Chang, “Question Identification on Twitter”, Proceedings of the 20th ACM International Conference on Information and Knowledge Management, New York, USA, 2011.</mixed-citation>
                    </ref>
                                    <ref id="ref4">
                        <label>4</label>
                        <mixed-citation publication-type="journal">Z. B. Özger ve B. Diri, “Sınıflandırma Tabanlı Türkçe Soru Algılama”, Akıllı Sistemlerde Yenilikler ve Uygulamaları, İzmir, Türkiye, 2014.</mixed-citation>
                    </ref>
                                    <ref id="ref5">
                        <label>5</label>
                        <mixed-citation publication-type="journal">C. Cengiz ve B. Diri, “Türkçe Tweetlerden Soru İfadelerini Bulmak”, Sinyal İşleme ve Uygulamaları Kurultayı, Türkiye, Nisan 2013.</mixed-citation>
                    </ref>
                                    <ref id="ref6">
                        <label>6</label>
                        <mixed-citation publication-type="journal">Google Code Archive, https://code.google.com/archive/p/zemberek/, 2017.</mixed-citation>
                    </ref>
                            </ref-list>
                    </back>
    </article>
