Contemporary marketing communication intensively implements the potentials of information technology and software tools and contributes to development of digital and electronic marketing. It tries to use social networking information about products, services and the company to shape a marketing mix and marketing strategy. Social networks are a channel of communication with potential and existing customers, they are a powerful means of shaping attitudes, opinions and image about the product or service. They are a direct customer communication and an in-house development tool. Exploring and understanding customer opinions have tremendous practical value for the enterprise because they provide proactive action and can direct the company's operational activities to customize the properties and quality of products or services to customer requirements. The paper reviews the opinions of users of social networks (potential or current buyers) about the brand by analyzing the content of their messages. Therefore, sentiment analysis is implemented in the paper. It is a process that finds the attitudes, feelings, or emotions of customers in textual data as an essential component of an image of a product or service. The main hypothesis of the paper is that social networks contribute to development of brand image. Designing a brand image can be effectively influenced through the social network. So first we explore the „presence” of the brand inside messages and communication between users of social networks Twitter and Facebook. Then, from both social networks we create word clouds and compare views, opinions, and internal images. On the basis of such analysis it is possible to make proactive marketing actions that can timely affect the brand image.

Huge amounts of data, in the form of messages on social networks, represent a challange for digital marketing and marketing analytics when meeting the requirements, needs and customer satisfaction with services or products. Marketing strives to be a part of the overall culture based on the data and to define marketing strategies that respond to consumers and thus to provide economic benefits for the company. Therefore, the focus of marketing analysis is on the data recorded at the social networks. This paper shows one possible integration of information technology and data mining tools, with the goal of visualizing the attitudes and opinions on the social networks in the form of a word cloud, which can then further be used to create marketing strategies and improve customer relations and customer service. Keywords: Text mining, word cloud, marketing analytics, R language, data mining

Integrated Marketing Communication  is both the system and the process of development and implementation of multiple forms of communication with the market. Its  long-term goal is to strengthen relations  with the  current customers but also to attract new customers. Therefore, the primary goal of integrated marketing communication is to have  influence on the behaviour of customers  in order to  shape and change their views and opinions. The marketing communication mix  consists of advertising, direct marketing communications, sales promotion, personal selling, public relations, publicity and outdoor advertising. This study  analyzes the attitudes and opinions of  young population regarding  the Internet as one of the most important media market communications. The instrument of data collection was a questionnaire and hypotheses were tested by using the chi-square test and confirmatory factor analysis.

Artificial intelligence is a computer-based analytical process that tends to create computational systems which we would incline to be called intelligent. Expert systems are the most important part of the artificial intelligence from economic perspective. Expert systems attempt to mimic the human thought process including reasoning and optimization. “Knowledge” is represented by a set of “if-then” rules in a form of knowledge base. The results of artificial intelligence system implementation in refining marketing customer strategy based on five customer behaviour factors: revenues, profit margin, market share, liquidity, long term value, and retention probability are presented in the paper. Customer marketing strategy depends on the combination of the value of these five attributes. Expert system helps a marketer to “drill down” into data and identify the most loyal customers, separates the customers into groups, and plans the adequate marketing strategy. Expert system for determining adequate marketing customer strategy is developed using Visual Prolog programming language. Visual Prolog has shown satisfactory application and developing power. Sažetak Umjetna inteligencija je na računalu temeljen analitički proces koji nastoji kreirati računalne sustave koje obično nazivamo inteligentni. Ekspertni sustavi su najvažniji dio umjetne inteligencije s ekonomskog aspekta. Oni pokušavaju oponašati čovjekov proces mišljenauključujući rasuđivanje i optimozaciju. Znanje se prikazuje u obliku skupa „if-then“ pravila u obliku baze znanja. Rezultati primjene sustava umjetne inteligencijeje oblikovanje marketing strategije prema kupcima pomoću pet faktora koji opisuju njihova ponašanja: prihodi, postotak razliie u cijeni, tržišni udjel, likvidnost, vrijednost kupca u dugom roku i vjerojatnost zadržavanja kupca. Marketing strategija prema kupcu ovisio kombinacijam vrijednosti tih atributa njihova ponašanja. Ekspertni sustavi pomažu „uroniti“ u podatke i identificirati najlojalnije kupce, klasificirati kupce u grupe, i planirati odgovarajuću marketing strategiju. Ekspertni sustav za određivanje adekvatne marketing strategije je razvijen uporabom programskog jezika Visual prolog. Visual Prolog je pokazao zadovoljavajuću primjensku i razvojnu moć.

Knowledge management is a general framework, concept that comprises the knowledge discovery process, learning techniques and collection of data mining algorithms. The paper researches the possibilities and advantages of supervised learning and knowledge base within the whole knowledge management in the process of market research. Knowledge management is a general concept of organizing, extracting, deployment und using the knowledge within an organization. The final goal is addition of the new knowledge in all functional areas of organization and use of knowledge to achieve strategic advantages and realize the defined and accepted goals of the organization. The paper is focused on marketing and discovering customers’ behavior determined by their demographic characteristics. It is shown in the paper that the supervised learning and knowledge base as components of knowledge management may be successfully implemented in marketing in description and forecasting of customers’ behavior. Sažetak Upravljanje znanjem je opći okvir, koncept koji obuhvaća proces otkrivanje znanja, tehnike učenja i skup algoritama data mininga. Rad istražuje mogućnosti i prednosti nadziranog učenja i baze znanja unutar cjeline upravljanja znanjem u procesu istraživanja tržišta. Upravljanje znanjem je koncept organiziranja, ekstrakcije, distribucije i uporabe znanja unutar organizacije. Krajnji cilj je dodavanje novih znanja u svim funkcijskim područijima i uporabe tog znanja radi postizanja strategijskih prednosti i realizacije definiranih i prihvaćenih ciljeva organizacije. Rad se fokusira na marketing i otkrivanje ponašanja kupaca određeno njihovim demografskim obilježjima.U radu je pokazano da nadzirano učenje i baza znanja kao komponente upravljanja znanjem se mogu uspješno implementirati u marketingu za opisivanje i predviđanje ponašanja kupaca.

The knowledge about customer preferences and behavior is fundamental for personalization of products and service. Personalization products and services are possible only if we have enough knowledge of who customers are, how they are similar among, how they behave. Knowledge discovery is process of transforming data into knowledge by adequate algorithms and software tools. In the paper is developed an approach that uses data in the form of transactional databases to construct accurate individual profiles. In developed data model are integrated transactional data and rules describing customer’s behavior. The rules are extracted from transactional data and cover individual customer behavior as well as the common behavior of all customers in the market segment. There are two rules types: first, for describing individual customer behavior and second, for the market behavior. Knowledge discovery plays a crucial role as an enabler to the organizations to integrate effective analytical data mining methods for prediction, classification, cluster, anomaly detection with data management and information visualization. Knowledge discovery is oriented to learning. In the process of learning we are implementing the functions of R language and this tool has shown satisfactory application and development power. Sažetak Znanje o ponašanju kupaca i njihovim preferencijama je ključno za personalizaciju proizvoda i usluga. Personalizacija proizvoda i usluga je moguća samo ako imamo dovoljno znanja o tome tko su kupci, koliko su međusobno slični, kako se ponašaju. Otkrivanje znanja je proces transformacije podataka u znanje primjenom odgovarajućih algoritamai softverskih alata. U radu je razvije pristup koji koristi podatke u obliku transakcijeke baze podataka kako bi se izgradio individualni profil. Pravila se ekstarhiraju iz transakcijskih baza podatakai otkrivaju pojedinačno ponašanje kupaca ali i njihovo zajedničko ponašanje unutar nekog klastera. Zato postoje pravila koje otkrivaju pojedinačno ponašanje kupca ali i cijelog tržišta (klastera). Otkrivanje znanja je tako orijentirano učenju. U procesu učenja primjenili smo fnkcije jezika R i taj softverski alat je pokazao zadovaljavajuću aplikacijsku i razvojnu moć.