20.500.12556/RUL-107364 PROFILIRANJE UPORABNIKOV V SISTEMU IP TELEVIZIJE NA OSNOVI VSEBINE, KONTEKSTA IN IMPLICITNEGA ODZIVA USER PROFILING IN IPTV SYSTEM BASED ON CONTENT, CONTEXT AND IMPLICIT FEEDBACK V današnjem povezanem svetu na vsakem koraku ustvarimo množico podatkov, imenovanih podatkovne sledi, v katerih se skrivajo informacije tako o posamezniku kot tudi o širši populaciji. Še posebej zanimivi so podatki, ki jih uporabniki takšnih sistemov podajamo implicitno in pogosto tudi podzavestno, saj na ta način obidemo zavestno filtriranje in samocenzuro. Po drugi strani pa so takšni viri podatkov pogosto omejeni, sporadično dostopni ter vsebujejo veliko šuma; posledično predstavljajo dodatne izzive pri analizi in interpretaciji rezultatov. Disertacija obravnava napredno obdelavo podatkov televizije na osnovi protokola IP (IPTV) v obliki podatkovnega toka uporabniških preklopov TVprogramov. TV-komunikatorje, ki so v uporabi v sistemih IPTV, lahko obravnavamo kot zmogljiva senzorska vozlišča, ki zbirajo velike količine diagnostičnih podatkov, ki vsebujejo tudi nekaj skritih informacij o aktivnosti uporabnikov, kakovosti ponujene storitve, delovanju sistema ipd. V disertaciji se osredotočamo predvsem na dogodke, ki jih generirajo gledalci, in analiziramo, kako lahko na osnovi psevdonimiziranega podatkovnega toka preklopov med TV-programi v omrežju IPTV rudarimo in pridobimo informacije o naravi same vsebine TV-programa, in mnenju uporabnika in tudi širše populacije o določeni tematiki. V disertaciji pokažemo, da je možno zaznati pojav neželenih vsebin (npr. televizijskih oglasov) z visoko natančnostjo in tudi, da lahko pristop razširimo v namen večdimenzijskega modeliranja uporabniškega vedenja in klasifikacije gledalcev. Predlagamo in opišemo ogrodje in metodo za ocenjevanje javnega interesa iz implicitnega negativnega odziva, zbranega iz populacije gledalcev IP-televizije. Naša raziskava temelji na podatkovnem toku preklopov med TV-programi, razširjenem s kontekstualno informacijo o vsebini. Predstavljeno ogrodje temelji na gradnji konceptov, profiliranju gledalca in kombinaciji njegove reakcije (zamenjava programa) in vsebine v namen modeliranja interesa gledalca in celotne populacije. Predstavljeno ogrodje naslavlja več slabosti v takšnih sistemih ter lahko zajame utrip širše populacije. Ogrodje validiramo na psevdonimiziranem podatkovnem setu realnega omrežja IPTV in pokažemo korelacijo pridobljenih rezultatov o več popularnih tematikah s klasičnimi dolgoročnimi raziskavami javnega mnenja prebivalstva. V namen validacije ogrodja za določitev javnega mnenja in interesa glede na implicitni odziv gledalcev sistema IPTV predstavimo hipotezo, da lahko implicitni odziv v obliki preklopov TV-programa, združen z metapodatki o vsebini, uporabimo tudi za modeliranje mnenja in interesa gledalcev. V ta namen oblikujemo kontroliran eksperiment in pridobimo eksplicitni odziv uporabnikov na množico splošno usmerjenih posnetkov novic. Poleg demografskih informacij anketiranci podajo svoje mnenje, interes in verjetnost preklopa TV-programa za vsak predvajan posnetek. Nadalje za vsak posnetek iz ankete določimo utežen vektor iz podatkov o vsebini posnetka, pridobljeni na osnovi podnapisov za gluhe; te podatke, kombinirane s podano verjetnostjo preklopa TVprograma, uporabimo za gradnjo modela, ki klasificira mnenje v pet kategorij na podlagi verjetnosti preklopa TV-programa in vsebine. Končno zgradimo še poenostavljen model, ki klasificira mnenje v pet kategorij na podlagi interesa, ki kaže linearno povezanost. Dodatno upoštevanje vsebine tudi v tem primeru zagotavlja boljšo natančnost in možnost analize anomalnih stanj. In today’s connected world we are creating sets of data, also called data trace where information about an individual as well as a broad population can be found, on every step. Especially interesting is the data that users of such systems express implicitly and often also subconsciously, as this is also a way to go around the conscious filtration and self-censorship. On the other hand, this kind of data is many times limited, sporadically available and contains a lot of noise. Consequently this presents additional challenges in analysis and final interpretation. The dissertation presents advanced data processing of IPTV data in the form of data stream of users’ channel changes. TV set-top boxes that are deployed in modern IPTV systems can be thought of as capable sensor nodes that collect vast amounts of diagnostic data, that also contains some hidden information about the users’ activity and the quality of service, system’s activity, etc. In the dissertation we focus mainly on the user-generated events and analyze how the pseudonymized data stream of channel change events received from the entire IPTV network can be mined to obtain insight about the content and about the user’s opinion, as well as broader population’s opinion about a certain topic. In the dissertation we demonstrate that it is possible to detect the occurrence of unwanted content, e.g. TV ads with high probability and also show that the approach could be extended to model the user’s behaviour and classify the viewership in multiple dimension. We propose and describe a framework and a method for estimating public interest from the implicit negative feedback collected from the IPTV audience. Our research primarily focuses on the channel change events and their correlation with the content information obtained from closed captions. The presented framework is based on concept modeling, viewership profiling, and combines the implicit viewer reactions (channel changes) and content into an interest score of the user and an entire viewership. The proposed framework addresses many disadvantages or concerns in these systems and can cover a much broader population. The framework is validated on a large pseudonymized real-world IPTV dataset provided by an ISP, and shows how the results correlate with different trending topics and with parallel classical long-term population surveys. We attempt to validate a framework for determining public opinion and interest through implicit feedback of IPTV viewers. Firstly, we address the hypothesis that implicit viewer feedback in the form of channel change events paired with the content metadata can be used to model viewers’ opinion and interest. For this, we design a controlled experiment to collect explicit users’ feedback by rating a set of general-interest news clips. In addition to collecting demographic information, we also survey viewers’ opinion, interest, and probability of channel change during each clip. Furthermore, we extract weighted feature vectors from the closed captions of the video; this data, combined with the reported probability of channel change, is used to build a model that classifies opinion in five categories based on probability of channel change and content. Next, we build a simplified model that classifies opinion in five categories based on interest, which shows a linear relationship; further consideration of the content however in this case provides better accuracy and possibility to analyze anomalous cases. televizija na osnovi protokola IP (IPTV) implicitni uporabniški odziv eksplicitni uporabniški odziv profiliranje uporabnikov modeliranje mnenja modeliranje interesa. IPTV implicit user feedback explicit user feedback viewership profiling opinion modeling interest modeling. true false false Slovenski jezik Angleški jezik Doktorsko delo/naloga 2019-04-04 09:55:03 2019-04-04 09:55:16 2022-08-19 03:49:11 0000-00-00 00:00:00 2019 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 1970-01-01 45861 Kren_Matej_-_PROFILIRANJE_UPORABNIKOV_V_SISTEMU_IP_TELEVIZIJE_NA_OSNOVI_VSEBINE,_KONTEKSTA_IN_IM.pdf Kren_Matej_-_PROFILIRANJE_UPORABNIKOV_V_SISTEMU_IP_TELEVIZIJE_NA_OSNOVI_VSEBINE,_KONTEKSTA_IN_IM.pdf 1 8D72DF4E5D208ABE7456ED3F670E6A9D d1be4458f62d1af0d2b1e3d80d53ced14dd7acb2ec23d76826f2b5ccfc30128e 6ac7f91b-a1b6-11eb-a523-00155dcfd717 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=118178 Fakulteta za elektrotehniko 0 0 0