Algorithms for classifying pre-tagged person entities in tweets into one of eight profession categories are presented. A classifier using a semi-supervised learning algorithm that takes into consideration the local context surrounding the entity in the tweet, hash tag information, and topic signature scores is described. In addition to the classifier, this research investigates two dictionaries containing the professions of persons. These two dictionaries are used in their own classification algorithms which are independent of the classifier. The method for creating the first dictionary dynamically from the web and the algorithm that accesses this dictionary to classify a person into one of the eight profession categories are explained next. The second dictionary is freebase, an openly available online database that is maintained by its online community. The algorithm that uses freebase for classifying a person into one of the eight professions is described. The results also show that classifications made using the automated constructed dictionary, freebase, or the classifier are all moderately successful. The results also show that classifications made with the automated constructed person dictionary are slightly more accurate than classifications made using freebase. Various hybrid methods, combining the classifier and the two dictionaries are also explained. The results of those hybrid methods show significant improvement over any of the individual methods.

Thesis advisor: Rosen Valchev / This thesis explores the impact of Donald Trump’s tweets related to China on the financial markets in the United States and China, particularly during the U.S.-China trade war period. The study collects financial variables of interest, including the USC-CNY exchange rate and several stock indices from both countries, at hourly intervals from January 2018 to December 2020, and uses OLS regression models to examine the immediate impact of Trump’s tweets on these variables. The study finds that Trump’s tweets related to China had an immediate impact on several financial variables, including a slight negative impact on the USD-CNY exchange rate, the U.S. stock market (S&P 500), the Chinese A-share stock market (CSI 300), and the U.S. industrials sector (MSCI USA Industrials index). Multiple regression analyses show that the number of tweets has a significant impact on the U.S. stock market and the U.S. industrials sector, while the number of retweets appears to be more market-moving than the number of favorites. The study concludes that Trump’s tweets during the trade war period were perceived by the market as a signal of a potential shift in U.S. trade policy towards China, leading to uncertainty and volatility in the financial markets. / Thesis (BA) — Boston College, 2023. / Submitted to: Boston College. College of Arts and Sciences. / Discipline: Departmental Honors. / Discipline: Economics.

Recently it is obvious that climate change has became a critical topic for human society. As climate change becomes more severe, natural disasters caused by climate change have increasingly impacted humans. Most recently, Hurricane Ida killed 43 people across four states. Hurricane Ida's damage could top $95 billion, and many meteorologists predict that climate change is making storms wetter and wider. Thus, there is an urgent need to predict how much damage the flood will cause and prepare for possible destruction. Most current flood damage estimation system did not apply social media data. The theme of this thesis was to evaluate the feasibility of using machine learning models to predict hurricane damage and the input data are social media and satellite imagery. This work involves developing Data Mining approach and a couple of different Machine Learning models that further extract the feature from the data. Satellite imagery is used to identify changes in building structures as well as landscapes, and Twitter data is used to identify damaged locations and the severity of the damage. The features of Twitter posts and satellite imagery were extracted through pre-trained GloVe, ResNet, and VGG models separately. The embedding features were then fed to MLP models for damage level estimation. The models were trained and evaluated on the data. Finally, a case study was performed on the test dataset for hints on improving the models. / Master of Science / Natural disasters affect Millions of people's lives each year and it is becoming even more severe because of global warming. To make rescue more efficient when the roads and bridges are cut, social media and satellite imagery are effective data sources to help estimating flood damage. With the growth of social media, it is obvious that the post and information from people on the Internet are powerful. Also, with image processing technology improves, the information extracted from satellite images is crucial. In this work we have developed a data mining approach along with different combinations of pre-trained models using neural networks, satellite imagery and archived data from Twitter to estimate flood damage. The data mining approach leverages keywords to identify the event in the history posts in the Twitter, more specifically, we attain the geo-location, time, language information from Twitter, also using pre-event and post-event images which satellite took to generate vectors and thus effectively acquire very useful embedding features. With vectored information from Twitter and satellite imagery, we use pre-trained models and generate damage level prediction. The final results suggest that the proposed approach has potential to create more accurate prediction by using multiple data as input. Furthermore, the estimate result by using only satellite images even outperformed the result using Twitter information, which is an unexpected result comparing to previous studies.

Media framing is present in everything one observes on social media. In athletics, mainly collegiate football, media framing goes into each and every detail that goes out to the public. With Power 5 sports, such as the Southeastern Conference, football is one of the most profitable, newsworthy and highly recruiting-based sports out there. Therefore, the planning that goes into all of the social media channels, specifically on the website called Twitter, is planned down to a science. However, there are times where that is not the case, as crises can arise at any given moment. This research explains how seven SEC football sports information contacts were interviewed about their social media habits for any and all situations that could arise on their platforms, and how they plan to handle it while keeping the brand, overall message and trust of its fanbases.

This study examines @FIFAmedia’s communication on Twitter, other users’ reactions to FIFA’s framing in their tweets, and on whether FIFA’s income from brand licensing was affected by the corruption scandal from 2015. By measuring FIFA’s framing and the reactions to it, a concrete comparison with FIFA's brand capital is enabled to provide further understanding of the impact the scandal had on the brand. All research questions are using a quantitative content analysis. The first two research questions are using Twitter and a sample period consisting of the periods: before, during and after the scandal. For the third research question FIFA's financial reports between the years 2013-2018 were interpreted to line up the numbers against each other to see if FIFA’s revenues from brand licensing have increased or decreased due to the scandal. The Framing Theory is used to answer the two first research questions about FIFA’s and Twitter users’ portrayal, whilst the Theory on Brand Equity is used to answer the third research question about FIFA’s brand equity. Previous research examines FIFA’s communication and Twitter users’ reactions to the tweets separately, but not in relation to each other. The result showed that FIFA communicates mostly about internal organizational activities and men’s football. The organisation often tweets with a link to its official website to update the followers on more information regarding their tweets. The result of other users' reaction to FIFA's framing in tweets was shown to be strongest after the corruption scandal was discovered. During this period, it is mainly private individuals who express negative thoughts towards FIFA’s tweets, as well as about FIFA as an organization. Finally, the results show that the scandal had an impact on FIFA's brand capital from licensing, where revenues increased vastly after the corruption scandal occurred, from the years 2016-2018. This result may be due to the fact that partners of FIFA sign multi-year contracts where a lot of money is involved, and that the financial capital between the partners is extremely important for the future of the organisations.

Twitter is one of today’s largest and most popular social networks. The users of the service generate huge amounts of data each day and rely heavily on the service helping them find interesting tweets in short time. The concept of hashtags aids in this practice but relies on the users choosing to include the correct and commonly used hashtags for the topic of their tweet. Hashtag recommendation has been a target of research before with varying results. This thesis proposes a method taking the location of the users into account when making recommen- dations. The method generated improved results over just using similar tweets as a basis for recommendation. Various factors like the handling of different variations of vocabulary in the tweets, how many tweets the suggestions can be picked from and how the combination of similarity and geographic ranking should function could affect the result. This leads to the conclusion that geographic data can be used to improve hashtag suggestions, but a different approach in handling similarity and alternative combinations of similarity and geographic ranking could cause another result. / Twitter är ett av nutidens största och populäraste sociala nätverk. Tjänstens användare producerar stora mängder data varje dag och förväntar sig att tjänsten ska kunna hjälpa dem att hitta intressanta tweets snabbt. Därmed finns konceptet med hashtags, men detta förutsätter att användare väljer att inkludera vanligt förekommande hashtags som på ett korrekt sätt avspeglar innehållet i tweeten. Automatisk rekommendation av hashtags har därmed varit ett populärt forskningsämne de senaste åren, med varierande resultat. Denna studie undersöker en rekommendationsmetod som väger in användarens geografiska position för att rekommendera så passande hashtags som möjligt. Resultaten visar att denna metod generellt rekommenderar mer passande hashtags än metoder som enbart rekommenderar hashtags genom att analysera likhet mellan tweets. Olika faktorer så som hanterandet av olika varianter av vokabulär, hur många tweets som metoden kan föreslå hashtags från samt hur kombinationen av rekommendation baserat på likhet och geografiskt position ska fungera, kan samtidigt påverka resultaten. Detta leder till slutsatsen att geografisk data kan användas för att förbättra hashtagrekommendation, men att ett annorlunda tillvägagångsätt i att hantera likhet och alternativa kombinationer av likhetsrangordning och geografisk rangordning kan leda till ett annorlunda resultat.

From a sample of over three million tweets from universities in the US, we described the characteristics of universities' communication about mental health on Twitter, including common keywords, bigrams, linked resources, and hashtags, as well as the frequency of dialogic communication and mental health tweets over time, especially in the context of the COVID-19 Pandemic. This study uses data mining to collect tweets from official university Twitter accounts and selected accounts of university wellness and counseling programs. Relevant tweets were collected from a large sample using keywords and bigrams relevant to mental health from the Twitter accounts of IACS accredited counseling centers. Universities have a unique opportunity to leverage communication through social media to benefit the mental health of their student body. Many users on social media discuss mental health and seek mental health information using the platforms. Findings from the literature on college student's health information seeking on social media are mixed; while a few university social media campaigns at various institutions have been examined, little is known about how universities use social media generally to communicate about mental health over social media.

Problemformulering och syfte Den här studien är relevant då den handlar om sådant som, via media, kan påverka konsumenters åsikter och därav också samhället på olika vis. Syftet med undersökningen är att studera och jämföra hur svensk nyhetsmedia har rapporterat om Elon Musk och Twitter/X. Uppsatsen redovisar resultaten av jämförelser mellan fyra olika svenska mediatypers gestaltningar och artikelmängder. Detta efter två uppmärksammade händelser som innefattar multimiljardären Elon Musk och den sociala medieplattformen Twitter/X. Händelserna är affärsmannens köp av Twitter (år 2022) samt logotyp- och namnbytet från Twitter till X (år2023). Metod och material Studien innefattar en kvantitativ innehållsanalys och resultaten kodades fram med hjälp av ett kodschema och en kodbok. Programmet Retriever användes för att söka efter samtliga artiklar under två väsentliga tidsperioder. Huvudresultat Uppsatsens huvudresultat är att samtliga fyra nyhetsmedier generellt sett hade gestaltat både Elon Musk och Twitter/X negativt i en övervägande majoritet av sina publicerade nyhetsartiklar under de två undersökta tidsperioderna. Det var totalt betydligt fler artiklar som publicerades efter Twitter-affären under 2022 än efter logotyp- och namnbytet under 2023. Kvällstidningen Aftonbladet hade totalt publicerat mest om Elon Musk och Twitter/X efter de två händelserna, men generellt sett så var det morgontidningen Dagens Nyheter som var mest negativ i sin gestaltning av affärsmannen och företaget.

No description available.

No description available.