192 research outputs found
Alexander Dugin and the Theory of a Multipolar World
No full textAleksander Dugin je politični filozof, sociolog ter politični aktivist in ideolog novoevrazijstva in z njim tesno povezanega projekta snovanja »četrte politične teorije«. Ta naj bi predstavljala politično-filozofski temelj sveta po koncu dobe prevladujočega vpliva Zahoda. Ugotavljamo, da je izhodišče multipolarne teorije zavrnitev a priornega preferiranja značilno modernih političnih konceptov, kakršen naj bi bil tudi nacionalna država. Tej zavrnitvi sledi postuliranje civilizacije kot političnega subjekta, ki odgovarja tako post-moderni globalni stvarnosti kot normativnemu izhodišču kulturnega oziroma civilizacijskega pluralizma. V drugem delu pregledamo nekaj recepcij Duginovega dela in avtorja postavimo v dialog z uveljavljenimi teoretiki na polju sociologije globalizacije in na polju kritične teorije, pregledamo avtorjevo umeščenost in vpliv v ruski javnosti in politiki, v slovenski politični in intelektualni sferi, ob koncu pa podamo nekaj izvirnih kritik in predlogov za nadaljnje raziskovanje. Delo povzema ugotovitev, da opredeljevanje Dugina kot skrajnodesničarskega teoretika in obskurnega ruskega filozofa ni zadostno, kar nas napeljuje na pomen nadaljnjega raziskovanja misli in dela tega kontroverznega misleca.Aleksander Dugin is a political philosopher, sociologist, political activist and ideologue of New Eurasianism and of the closely related project of developing the "fourth political theory", which is supposed to represent the political-philosophical foundations of the world after the end of the era of dominant Western influence. We note that the starting point of the multipolar theory is the rejection of a priori preference for the typical modern political concepts, such as the nation-state. This rejection is followed by the postulation of civilization as a political subject, which corresponds to both the post-modern global reality and to the normative axiom of cultural and civilizational pluralism. In the second part, we examine some of the receptions of Dugin\u27s work and put the author in dialogue with established theorists in the field of sociology of globalization and in the field of critical theory, we examine the author\u27s place and influence in the Russian public and politics, and in the Slovenian political and intellectual sphere. At the end, we give some original criticism and suggestions for further research. We conclude that defining Dugin as a far-right theoretician and an obscure Russian philosopher is insufficient, which leads us to the importance of further research into the thoughts and work of this controversial thinker
Content search and analysis through an interface implemented with the React library
No full textTema ovog rada je izrada usluge pod nazivom Movie Analyzer koja korisniku omogućava pretraživanje i analiziranje sadržaja o filmovima upotrebom programskog rješenja Solr za implementaciju tražilice i biblioteke React za izradu korisničkog sučelja u programskom jeziku JavaScript. U radu je detaljnije objašnjena svaka od korištenih tehnologija te je dana usporedba sa sličnim ili konkurentskim tehnologijama. Detaljno je opisana arhitektura usluge, postupak dizajniranja indeksa, uvoz podataka o filmovima iz relacijske baze podataka kao i funkcionalnosti pretraživanja i specijaliziranih vrsta preporučivanja filmova u korisničkoj web aplikaciji.The topic of this thesis is development of service named Movie Analyzer which enables the user to search and analyze movie information by using Solr as a search engine and the React library for graphical user interface written in JavaScript. The project contains detailed descriptions for each of the used technologies and also provides a comparison with similar or competing technologies. The architecture, index creation, importing movie data from a relational database, functionalities of search, specialized movie recommendations from the user web application, are all described in detail
Social networking of machines: case study of a safe house
No full textModerne tehnologije ulaze u sve više života svakodnevno. S pojavom platformi za pametna kućanstva, automatizirani domovi više nisu daleka budućnost. Platforme za pametna kućanstva omogućavaju svakome da upravlja svojim domom sa samo par klikova ili dodira. Pametni uređaji unutar doma da uče o korisniku i prilagođavaju se njegovim navikama. Danas ljudi mogu napraviti vlastitu platformu za pametno kućanstvo pomoću sklopovlja poput Raspberry Pija i Arduina, cjenovno pristupačnog gotovo svima. Jedan od najvažnijih segmenata pametnog kućanstva je sigurnost doma i obitelji.
Kako bi se pomoglo obiteljima da bolje funkcioniraju i kako bi se povećala sigurnost djece u njihovim domovima, razvijena je IoT platforma Juvo – Home Friend. Juvo – Home Friend pomaže roditeljima da se nose sa svojom potrebom da zaštite i nadziru svoje dijete, pogotovo u slučaju djece s autizmom. Pružajući roditeljima veću kontrolu nad kretnjom svoga djeteta unutar vlastitog kućanstva, roditelji se konačno mogu opustiti i izbjeći određenu količinu stresa.
Platforma Juvo – Home Friend se sastoji od senzora koji su postavljeni na potencijalno opasna mjesta unutar kućanstva. Platforma također uključuje bluetooth narukvicu koja aktivira senzore svaki puta kada se pojavi preblizu pametnim senzorima. Senzori tada šalju notifikaciju roditeljima putem aplikacije na pokretnom uređaju. Pošto se roditeljski stres direktno prenosi na njihovu djecu, smanjujući roditeljski stres uvelike se doprinosi boljitku cijele obitelji.Modern technologies are entering more and more lives every day. With the advent of smart home platforms, automated homes are no more far future. Smart home platforms allow everyone to manage their home with just few clicks or taps. Smart devices inside automated home are capable to learn about users and adapts to their habits. Nowadays people can build their own smart home platform with hardware like Raspberry Pi and Arduino, affordable to almost everyone. One of the most imported segment of smart home is home and family safety.
To help families in their better functioning and to increase the safety of children in their home, Juvo – Home Friend IoT platform is developed. Juvo – Home Friend helps parents to better cope with their need to protect and supervise their children, particularly in case of children with autism. By giving parents a higher control of movement of their children inside of their home, parents finally have a chance to relax more and to fell less stressed.
Juvo – Home Friend platform consists of sensors which are placed on potentially dangerous places inside the home. It also includes Bluetooth bracelet which activates the sensors every time the bracelet comes too close to smart sensor. The sensors then send a notification to the parents via mobile application. Since parent's stress is directly reflected on their children, reducing parenting stress is a major contribution to the wellbeing of the whole family
A program library for experiment-driven knowledge creation within a power trading simulation platform
No full textKao dobar pristup za modeliranje liberaliziranog tržišta pokazao se model zasnovan na programskim agentima u kombinaciji sa simulacijom. Jedna takva simulacija pod nazivom Power TAC obrađena je u ovom završnom radu. Glavni akter je programski agent koji simulira brokera na tržištu električne energije. On kupuje električnu energiju od velikih proizvođača na veleprodajnom tržištu, te pomoću odgovarajućih tarifa pojedinim potrošačima prodaje na maloprodajnom tržištu. Cilj je u natjecanju s drugim agentima ostvariti najveći profit, što je ujedno i kriterij pobjede.
Jedan od dosadašnjih nedostataka kostura programskog agenta bio je nemogućnost učenja kroz prethodne simulacije. Naime, po završetku jednog eksperimenta sve informacije o njemu bile bi zaboravljene, odnosno nisu se pohranjivale. Zadatak programske knjižnice koja je razvijana u sklopu ovog Završnog rada bio je omogućiti pohranu ovih podataka te pristup istim u nekim budućim s ciljem izrade programskog agenta koji je u stanju stvarati i koristiti znanje o prošlim simulacijama.The agent-based model in combination with an simulation has proved to be good approach to modeling liberalized market. One of those simulations named Power TAC has been examined in this thesis. The main actor is an agent who acts as a broker on the electrical energy market. The agent is buying the energy from generating companies on the wholesale market, and through appropriate tariffs he is selling it to customers on the retail market. The main goal of the competition is to achieve the highest profit among other agents, what is at same time the criteria for win.
At the moment the structure of the agent had some shortcomings, one of them was the inability of learning through previous simulations. At the finish of an experiment all information regarding the experiment are lost, or better said they do not save. The task of the program library that was in this thesis discussed was to enable storage of this data and access to the data in the case of some future simulations with the end goal of constructing a more competitive agent
Forecasting consumer interest in information services by using semantic-aware model
No full textUzimajući u obzir neprestani rast konkurencije, uvođenje novih tehnologija te nove usluge koje se zasnivaju na njima, davatelji usluga moraju uvesti mehanizme za kvalitetno predviđanje koje postaje temelj pravovremenom uočavanju novih prilika na tržištu, prepoznavanju potencijalnih pogrešaka, planiranju resursa te u konačnici financijskom planiranju. Modeli rasta su jedna od najčešće korištenih metoda predviđanja na području informacijskih usluga. Međutim, korištenje isključivo modela rasta ima određene nedostatke kao što su ograničena preciznost te kašnjenje zbog potrebe za uzorkom povijesnih podataka u svrhu izračuna parametara. U disertaciji je predstavljen nov pristup u predviđanju rasta interesa korisnika informacijskih usluga zasnovan na poznatim modelima rasta te semantičkom rasuđivanju kojim se umanjuju navedeni nedostaci postojećih modela rasta. Novi pristup zasniva se na tri koraka. Prvi korak je definicija profila informacijske usluge sastavljenog od semantičkog opisa, koji omogućava automatiziranu usporedbu usluga i modela rasta koji opisuje interes korisnika za uslugu. Drugi korak je predviđanje interesa korisnika za informacijske usluge zasnovano na usporedbi nove s postojećim uslugama primjenom semantički-svjesnog modela. Treći korak je evaluacija predloženog pristupa za predviđanje interesa korisnika za informacijske usluge na studijskom primjeru YouTube videoisječaka. Rezultat evaluacije napravljene pomoću implementiranog radnog okvira za predviđanje na studijskom uzorku predstavljen je kroz mjere odstupanja predviđenih vrijednosti od stvarnih, te kroz analizu utjecaja pojedinih parametara algoritma za predviđanje interesa na preciznost predviđanja, odnosno na mjere odstupanja.Information and communication services' market is characterised with the constant growth of competition as well as continuous emergence of new technologies and, consequently, new services based on these technologies. To tackle market challenges, service providers must improve their business processes by introducing new mechanisms into existing planning and decision making processes. These mechanisms primarily relate to the timely anticipation of potential market opportunities, as much as potential mistakes, resource planning, and finally financial forecasting. Growth models provide a possibility for forecasting consumer acceptance for services, which makes them one of the possible solutions for these challenges. However, commonly used growth models have certain deficiencies which have to be mitigated by using other methods. These deficiencies are primarily limited precision and delays in forecasting caused by the need for at least a minimum set of historical data in order to calculate model parameters. This dissertation presents a new approach in forecasting of consumer interest for information services based on commonly used growth models and semantic reasoning. This new approach consists of three steps. The first step is the definition of information service semantic profile consisting of a semantic description, which enables automated service matchmaking, and growth model, which describes the consumers' interest in that particular service. The second step is forecasting consumers' interest in information services based on similar services determined by using semantic reasoning. The final step is an evaluation of the proposed approach using YouTube video clips as a case study. Chapter One – Forecasting in information and communication technology industry The first chapter provides an introduction to forecasting in information and communication technology domain. Most common forecasting methods can be divided into two groups: (i) methods based on estimation; and (ii) methods based on quantitative data. These methods are used for predicting certain indicators that describe the service and product lifecycle. One of the most important indicators is consumers' interest for a certain service or product. Observing various patterns in services' lifecycle, five major phases could be identified: (i) development; (ii) introduction; (iii) growth, (iv) maturity; and (v) decline. Growth models are one of the most commonly used forecasting methods in the information service domain, especially when describing the initial phases in the service lifecycle. Some of the most common growth models include: (i) logistic model; (ii) Bass model; (iii) Richards model; (iv) recursive models; and (v) multi-logistic models. This research is based on the Bass model, due to its characteristics which have made it efficient in modelling the initial growth of consumers' interest in this particular domain. Chapter Two – Semantic reasoning One of the main downsides of using growth models is the necessity of sufficient historical data for model parameter calculation. When there is no sufficient data, a different approach must be used for calculating these parameters. This research is based on the idea that similar services have similar growth under similar circumstances. Semantic reasoning is proposed to quantify similarities between services, thus creating the ground for an innovative approach in growth modelling. Semantic reasoning is primarily used for generating semantic profiles for information services, which can then be compared taking into account the real meaning of each attribute, attribute value data types, and relations between resources that describe a certain pair of services. Matchmaking of two semantic profile is performed starting on attribute level, and then gradually aggregating these similarities towards final profile similarity taking into account all attribute similarities and their respective weights. Such semantic matchmaking algorithm results in a numeric description of the similarity between services in the interval [0,1], where 0 (zero) means that the services have absolutely nothing in common, and 1 (one) means that the services are identical. Chapter Three – Consumer interest forecasting model for information services The third chapter presents the generic consumer interest forecasting model for information services. The model consists of five key entities that participate in service provisioning and acceptance forecasting: (i) service provider; (ii) contributors; (iii) consumers; (iv) consumer interest forecasting framework; and (v) data storage system. The service provider is the primary facilitator that enables infrastructure for information service provisioning. Contributors are the producers of resources that are put at consumers' disposal via service providers. Consumers are the persons whose consumption of particular service results in acceptance growth for that service. The forecasting framework performs data collection and semantic profiling of the services, semantic matchmaking of the created profiles, and consumer interest growth forecasting. Data storage system is used for storing semantic profiles and acceptance data for observed services. Chapter Four – Proposed implementation of consumer interest forecasting framework for information services Fourth chapter provides a more detailed insight in the forecasting framework components and their functionalities. The proposed framework consists of four modules. Semantic profiling module performs consolidation of data that describe information services and historical acceptance data used for calculation of growth model parameters. Semantic matchmaking module compares service profiles according to proposed algorithm through separate comparison for each attribute, and final aggregation of the individual attribute similarities into profile similarity. Module for growth modelling based on historical data uses the historical acceptance data in order to calculate the growth model parameters and respective deviation measures: (i) simple relative deviation; and (ii) weighted relative deviation. New service growth modelling module calculates growth model parameters based on similar service model parameters. The chapter is concluded by a flowchart representing the process of framework evaluation through a case study based on YouTube video clips. Chapter Five – Data collection and semantic profiling for YouTube video clip streaming service The fifth chapter presents the implementation of the framework segment responsible for fetching data about YouTube video clips and translating them into semantic profiles, thus creating a data sample for the framework evaluation. The first step in sample preparation is retrieving the basic video clip data in accordance with eligible combinations of attribute values for attributes which are considered relevant in the sense of sample representativeness. After having created the initial sample, the next step includes obtaining information about related video clips and video clips published by same contributors, all through the YouTube API. The final sample is formed after retrieving detailed data about the video clips and eliminating those whose data was of insufficient quality for automated processing. Detailed video clip description data and historical acceptance data is then used for generation semantic profiles according to the presented structure. Chapter Six – YouTube video clip semantic profile matchmaking The sixth chapter provides a more detailed insight into the implemented semantic matchmaking algorithm. Video clip attributes are divided into two groups: (i) ones related to the content description; and (ii) ones related to technical characteristics. The algorithm provides different methods of comparison with regards to the attribute value domains: (i) trivial identity check between two values used for attributes with very limited domain; (ii) similarity matrix for attributes with larger but limited domain; (iii) text comparison based on three text similarity measures; (iv) semantic resource comparison based on four measures that define their similarity and relationship; and (v) publish date comparison. Each method is presented through the respective example. The final step of the algorithm is summarising individual attribute similarities into the final service similarity. Chapter Seven – Viewership growth modelling for YouTube video clips based on historical acceptance data Framework segment responsible for growth model parameter calculation based on historical acceptance data uses weighted least squares method for determining the Bass model parameters. Weight determination method can be set as an input parameter to emphasise a certain part of the growth period, most commonly the later stages so the extrapolation of the model can provide better insight into the upcoming period and enable more precise forecasting. This research presents four distinct weight determination methods: (i) identical weights; (ii) arithmetical progression; (iii) geometrical progression; and (iv) logistic function. These methods are benchmarked through examples and respective deviations. Chapter Eight – Viewership growth modelling for YouTube video clips based on similar video clip acceptance growth The final chapter presents the growth forecasting algorithm for YouTube video clip viewership. Inputs for the algorithm are similarities with the remaining video clips in the sample, and their growth model parameters. Evaluation of the proposed algorithm, which also represents the final scientific contribution of the thesis, is performed as a forecasting simulation for a subset of the case study sample, called the evaluation sample. Similarity with all other video clips is calculated for each of the video clips from the evaluation sample, after which the selection of the most similar video clips is done. Using growth model parameters of these most similar video clips, the algorithm calculates growth model parameter which enables growth forecasting for evaluation sample video clips. Forecasting precision is evaluated through observing the influence of three forecasting parameters: (i) method for selection most similar video clips; (ii) weight determination method for least squares method; and (iii) forecasted growth period. Conclusion The thesis proposes a new approach to address the problem of consumer interest forecasting for information services. The proposed approach is based on the hypothesis that similar services have similar acceptance growth within similar circumstances. In accordance with that hypothesis, the research is focused on service matchmaking mechanism and a forecasting algorithm that uses calculated similarities between services and acceptance data for existing services in order to forecast acceptance growth for a new service. Such an approach eliminates the need for an initial acceptance data set in the process of determining growth model parameters. To evaluate the proposed approach on a case study, a framework is implemented and used for generating a case study data sample consisting of 7,683 video clips. The framework enables semantic profiling of the video clips based on their content descriptions, technical characteristics, and historical acceptance data, comparing these profiles based on attribute value matching, calculating growth model parameters from historical acceptance data, and, finally, acceptance growth forecasting based on similar services. The acceptance forecasting algorithm is evaluated on an evaluation sample consisting of 100 video clips through two defined deviation measures. The evaluation is based on observing deviation measures in correlation to three input parameters: (i) similar video clip selection method; (ii) weight determination method for the least squares method; and (iii) forecasted growth period. The most precise forecasting was achieved when taking into consideration only video clips with similarity greater than 0.90, and weights based on logistic function for the period of 90 days. Influence of each parameter is analysed through a total of 144 different combinations of input parameters. The conclusion is that the „absolute method“ with high similarity threshold (0.90) provides greater precision, but bearing in mind that it is applicable only for a very small part of the evaluation sample. Reducing that threshold, or using the „relative method“ for similar video clip selection, broadens the applicability, but at the cost of reduced precision. Weight determination method generally does not influence the forecasting precision, but in combination with certain growth periods can result in greater precision. Future work in means of improvements should include an extension of the data sample, and increase in forecasting precision. Besides adding additional video clips in the data set, further attributes should also be included in the research, especially having in mind constant YouTube API upgrades. Semantic matchmaking algorithm should be addressed from two aspects. First consists of a more detailed analysis of the correlation between specific attributes and acceptance growth in order to adjust the weights for the attributes and their respective groups. The second aspect is optimising the parts of the process that have proven to be time-consuming. One approach for this optimisation is rationalising the usage of the algorithm through video clip clustering. Additionally, other growth models should also be considered for acceptance growth approximation (i.e., Richards model)
Networking of machines: case study based on the Raspberry Pi microcomputer
No full textStrojna (M2M) komunikacija je koncept koji definira pravila i odnose između uređaja dok surađuju. To podrazumijeva visoko automatizirano korištenje skupa uređaja istovremeno, bez ikakve potrebe za ljudskom interakcijom. U ovom diplomskom radu su opisane pojedinosti o M2M komunikaciji. Glavni fokus je bio na integraciji mikro-računala Raspberry Pi s operativnim sustavom Android.
Studijski primjer sustav ApPi je kontolor temperature i vlažnosti zraka koji može pomoći u održavanju i očitavanju zapisa o izmjerenim podacima na Android pametnim pokretnim telefonima, putem Interneta. Raspberry Pi čita temperaturu i vlažnost te šalje podatke u oblak za pohranu. Android aplikacija čita podatke iz oblaka te crta grafove na temelju toga.Machine-to-Machine (M2M) communication is a concept that defines the rules and relationships between devices while cooperating. It implies a highly automated usage of a set of devices simultaneously, without any need for human interaction. In this Master's thesis, there have been described details about M2M communication. Main focus was on integration of Raspberry Pi with the operating system Android.
Study example ApPi is a temperature and humidity monitor that can help keeping a track on the data remotely via the Internet on an Android Phone. The Raspberry Pi reads temperature and humidity and sends the data to the cloud storage. Android application reads the data from the cloud and graphs it
Server-based system for collecting, storing and processing connected vehicle data
No full textS obzirom na trenutno stanje u autoindustriji koje podrazumijeva okrenutost prema povezanosti vozila, bitno je razvijati sustave namijenjene okruženju u kojem vozila generiraju veliku količinu podataka. Iz tog razloga razvija se poslužiteljski sustav za prikupljanje, pohranu i obradu podataka s umreženih vozila opisan u ovom radu. Funkcionalnosti sustava su mnoge i međusobno različite, od praćenja lokacijskih koordinata i brzine vozila, navigacije i obrade podataka u stvarnom vremenu, do analize i statistike velikih skupova povijesnih podataka. Zbog toga je stavljen naglasak na fleksibilnost, skalabilnost i nadogradivost sustava, što se ovdje ostvaruje korištenjem modernih tehnologijama otvorenog koda kao što su Apache Kafka, Apache Flume, MongoDB, uz pridržavanje načela arhitekture Lambda.Given the current state of the automotive industry, which implies orientation towards vehicle connectivity, it is essential to develop systems for such environment in which vehicles produce large quantities of data. For this reason, a server based system for collecting, storing and processing data from connected vehicles is being developed. The functionalities of the systems are many and mutually different, from tracking location and vehicle speed, navigation and data processing in real time to analysis of large sets of historical data. Therefore, the emphasis has been put on flexibility, scalability and system upgradability, which are here achieved using modern open source technologies such as Apache Kafka, Apache Flume, MongoDB and others, in compliance with the principles of Lambda architectural style
Anonymization of user data in provisioning information and communication services
No full textU ovom diplomskom radu obrađena je tema anonimizacije podataka s naglaskom na podatke medicinskog kartona pacijenata. Informacije o lijekovima, operacijama, ili bolestima od kojih pacijent boluje vrlo su osjetljive prirode. Re-dentifikacija takvih podataka predstavlja ozbiljan propust koji bi uzrokovao povrede privatnosti. Zbog osjetljive prirode podataka zdravstvene domene, zakonskim regulativama je ograničena njihova obrada i pohrana. U radu su navedeni primjeri neadekvatno anonimiziranih podataka te opasnosti za privatnost pacijenata koje mogu biti uzrokovane njihovom objavom. Dan je pregled postojećih modela zaštite podataka i tehnika za njihovu izvedbu. Praktični dio rada sastoji se od predloženog modela privatnosti za anonimizaciju podataka i izvedbu anonimizacije predloženim modelom uz pomoć alata ARX za anonimizaciju podataka.This thesis discussed the topic of Data Anonymization focusing on patients healthcare data. Informations about medicine, operations or dieses that the patient is affected by and are sensitive in nature. Re-identification of that data poses a great omission that could cause violation in privacy. Because of sensitive nature of Healthcare data domain, processing and storing the said data is limited by legalisation rights. In this thesis there are examples of inadequate anonymized data with and kind of risk that could violate privacy of the patients by announcing said data. An overview of existing data security models and techniques for their implementation. Practical part of thesis is composed of proposed model of data anonymization and the implementation of proposed model anonymization with help of ARX anonymization tool
Analysis of social media marketing in sports industry: the case of Premier League
No full textOvaj se diplomski rad koncentrira na marketing zasnovan na društvenim mrežama, marketing na tražilicama i njihove prakse koje koriste top 5 brendova u Engleskoj Premier Ligi. Nakon generalnog pregleda marketinga i uvoda u marketing zasnovan na društvenim mrežama, marketing na tražilicama i sportsku industriju, model Engleske Premier Lige je sastavljen za svaku od promatranih sezona. Radni okvir za kvantitativnu i kvalitativnu analizu marketinga zasnovanog na društvenim mrežama i marketinga na tražilicama je dizajniran i implementiran. Ključni identifikatori performansi su potom definirani te je statistička, korelacijska i regresijska analiza provedena s ciljem da se istraže ključni identifikatori performance, njihove sličnosti i različitosti te što utječe na njih. Rezultati su pokazali da postoji značajna razlika između istih ključnih identifikatora performansi za različite brendove, da postoji jaka korelacija između tih identifikatora performansi unutar brendova te su doneseni zaključci koji događaji utječu na koji od identifikatora unutar brenda i koji događaji generalno utječu na pojedine identifikatore.The thesis concentrates on social media marketing, search marketing and their practices used by the top 5 brands in the English Premier League. After an overview of marketing in general and introduction to social media marketing, search marketing and sports industry, English Premier League model was constructed for each of the observed seasons. Analysis framework was designed and implemented for qualitative and quantitative analysis of social media and search marketing in sports industry. Key performance indicators were defined and statistical, correlation and regression analysis was conducted to explore key performance indicators, similarities and differences among them and find out what influences them. Finding have shown that there is significant difference among same key performance indicators for different brands, strong correlation exists among key performance indicators observed in brands, conclusions have been made which features influence which brands key performance indicators, and which features influence individual key performance indicators in general
Profile analysis of effects connected to bot affinity scores based on sentiment and emotion on Twitter social network
No full textDruštveni botovi danas imaju značajnu ulogu u online komunikaciji. Opažanja rastućeg utjecaja botova na društvenim mrežama poput Twittera služe kao motivacija za istraživanje efekata koje njihovo emocionalno ponašanje ima na druge korisnike i ekosistem društvenih mreža. Svrha ovog rada je istražiti efekte koje grupe računa imaju s obzirom na vjerojatnost da su oni botovi s naglaskom na istraživanje povezanosti ljudi i botova. Koristeći korelacijsku i regresijsku analizu, u sklopu rada je analiziran skup podataka koji sadrži 17 milijuna tweetova. Inicijalni skup podataka i NRC leksikon su zatim korišteni kako bi se izračunale vremenske serije emocija kao mjera za intenzitet emocija koje grupe računa izražavaju. Korelacijska analiza je pokazala kako su grupe afiniteta usklađene s obzirom na volumen emocionalnih riječi koje objavljuju te kako su emocije povezane unutar afinitetnih grupa. Regresijska analiza je upotrebljena kako bi se istražio utjecaj emocija iz prijašnjeg sata na pojedine emocije u sljedećem satu. Rezultati pokazuju kako su ljudske emocije bolje u predviđanju negativnih emocija koje botovi izražavaju od samih emocija botova iz prijašnjeg sata što ukazuje na efekt botova da „pojačavaju“ ljudske negativne emocije. Rezultati također ukazuju da je emocija „iznenađenja“ koju izražavaju sve afinitetne skupine značajan prediktor mnogih ljudskih emocija. Ovi rezultati pokazuju postojanje razlika u emocionalnom ponašanju koje prenose botovi i ljudi na razini sata, ali daljnje istraživanje s fokusom na veći period razmatranja bi potencijalno mogao voditi k boljem razumijevanju efekata koje emocije izražene od botova imaju unutar ekosistem društvenih mreža.Social bots nowadays have a major part in online communication. Observations of the rising influence of bots on social media platforms such as Twitter serve as motivation for exploration of the effects that their emotional behaviour has on other users and the social media ecosystem in general. The purpose of this study is to investigate effects that groups off account have with regards to the likelihood that they are bots with emphasis on exploring the relationship between human and bot accounts. Using correlation and regression analysis, a dataset of over 17M tweets that mention Bitcoin cryptocurrency was analysed. The dataset and NRC lexicon were used to compute emotion time series as an intensity measure of conveyed emotions by a group of accounts. Correlation analysis showed how affinity groups are correlated with regards to the volume of emotional words they post but also how emotions are correlated inside affinity groups. Regression analysis was employed to explore how hourly emotion shares depend upon previous hour emotions. Results show human emotions are a slightly better predictor of negative bot emotions than bot emotions which indicates the effect that bots “amplify” negative emotions. Results also indicate that “surprise” conveyed by all affinity groups is a significant predictor of many human emotions. These results show that differing emotional behaviour exists between affinity groups on the hourly time frame, but further research focused on larger time frames could lead to a potentially better understanding of the effects that bot-conveyed emotions have inside the social media ecosystem
- …
