Despite the entry of many media services, television remains the most used media service and accounts for the largest advertising spending globally. One of the main metrics for measuring the successfulness of a television advertising campaign is reach, the percentage of the intended target audience that has seen the television advertisement. To help plan television advertisements, the industry aims to find new methods for predicting television advertisement reach more accurately. Therefore, it is of interest to explore the possibility to utilize machine learning regression models. This report examines how well four machine learning regression models are suited for predicting reach based on historical campaign data. The results indicate that the best-performing model is an XGBoost model with a mean absolute percentage error just below 5%. The report also describes which features impact reach the most and if data augmentation can improve the performance of the machine learning models.

Stereotyping of male and female roles is currently the subject of many discussions in various spheres of society. Stereotypes are widely used in the advertising industry, where they aim to make it easier for potential customers to identify with the product and support the company's image. Choosing the right gender for a particular advertisement depends on the nature of the product as well as on the target group. Some product groups are more gender- differentiated than others. An exemplary group are household cleaning products. Related advertisements traditionally show female characters more often than male characters. However, the time when cleaning products were promoted exclusively by women is over and nowadays, men appear in these kinds of advertisements too. The growing number of characters who are portrayed in non-stereotyped gender roles in television commercials began to be discussed more prominently as early as the end of the 20th century. From a sociological point of view, the gender role is a set of socially defined behavioral norms, reflecting what society usually expects from a man or a woman. For this reason, the portrayal of characters in inverse gender positions that is a step in the right direction in the pursuit of greater gender equality in society. The aim of this work is to find out...

This paper's aim is to critically describe and use Michel Foucault's method archaeology for discursive description of contemporary television beer advertisements broadcasted in the Czech Republic. Theoretical part tries to define terms as denounce, discursive formation and discourse and propose their possible usage in practical research. The paper supposes that television beer advertisements are governed by the same discourse which was used in other beer advertisement and all advertisements form a coherent whole. Analytical part's aim is to describe this coherent whole from the aim of discourse and specific chose of denounces that form picture of beer and its role in a men world. Key words: Foucault, discourse, archaeology, television advertisement, beer

No description available.

[pt] Esta pesquisa tem como objetivo estudar o gênero discursivo propaganda televisiva e as interações verbais aí presentes sob a perspectiva bakhtiniana. O corpus principal da pesquisa compõe-se de dados retirados de algumas propagandas televisivas, tendo sido gravadas e transcritas 11 propagandas da empresa FIAT Automóveis do Brasil, produzidas no período de 2000 a 2003. A análise das propagandas televisivas foi realizada com base nos pressupostos da teoria de Bakhtin (1981, 1992 e 1997), considerando-se conceitos de gênero, interação verbal, dialogismo, vozes discursivas, intertextualidade e ironia. A partir dos resultados da análise, propomos a classificação do gênero propaganda televisiva como um gênero intersemiótico complexo. A análise dos dados permitiu também caracterizar a propaganda televisiva como um gênero em que há a fusão do próprio gênero propaganda com o seu veículo de suporte, a televisão. O estudo das interações verbais mostrou que este gênero reflete aspectos histórico- sociais, valores e estereótipos, por meio das vozes ideológicas da sociedade, que permeiam o discurso. Este trabalho nos possibilita confirmar que a língua é um fenômeno social, histórico e ideológico e que o contexto é muito importante para a compreensão do que é dito ou do que se quer dizer em uma propaganda televisiva, que se constitui como um enunciado social (Bakhtin, 1981, 124). / [en] The purpose of this research is to study the genre television advertisements and verbal interactions under Bakhtin`s perspective. The main corpus of the study is composed of data from TV ads, having been recorded and transcribed 11 samples of Brazilian car advertisements of FIAT Automobile Company, produced from 2000 to 2003. The analysis of the ads was based on theoretical concepts extracted from Bakhtin`s language theory (1981, 1992 and 1997), considering genre, verbal interaction, dialogism, discursive voices, intertextuality and irony. Based on the results of the analysis, the classification of television advertisements as a complex intersemiotic genre is proposed. Data analysis also led into the characterization of TV ads as a fusion of the advertisement genre itself together with its supporting medium, the television. The analysis of verbal interactions indicates that this genre reflects socio-historical aspects, values and stereotypes of a particular period of time through ideological voices, which are intertwined in discourse. This research confirms that language is a social, historical and ideological phenomenon and that context is very important for the understanding of what is said or of what one wants to say in a television advertisement, which is itself a social utterance (Bakhtin, 1981, 124).