by Damian Grimling | Oct 24, 2023 | Politics and Social
The results of the October 15, 2023 elections have had a stimulating effect on the prices of many financial instruments. Sentimenti analysts surveyed with the proprietary tool SENTITOOL, the period from October 11 to 18, measuring the level of the investor confidence index, defined as the intensity of confidence emotions expressed in posts made on social media. The study was based on an analysis of 1,517 such posts relating to diversified financial instruments.
Changes in the trust index
The final days of the campaign and the ordered election silence in effect especially on Saturday, October 14 caused investors to take a distinctly wait-and-see position. This resulted in a drop in the daily confidence index by an average of 3 percentage points from the level recorded as recently as October 12. As expected, only the successively announced results on voter turnout and preliminary exit poll data caused a decisive change in the level of the confidence index, which reached an increase of 11 percentage points on October 15.
Such a change in sentiment has boosted financial markets. A prime example of such a revival was the WIG20 bourse, which had already risen 5.3% from its last quote on October 16. In the following days, too, a cause-and-effect relationship can be seen between the confidence index and the WIG20 bourse.
Confidence index on Election Day
There was an interesting development of the confidence index on election day itself,October 15. An hour-by-hour analysis shows what dynamic fluctuations it underwent. Thus, after the opening of polling stations, it had an upward trend, which was slowed down by the turnout data at 12:00 p.m. The subsequent data at 5:00 p.m., combined with exit poll data, resulted in a dynamic (by 11 percentage points) increase in the confidence index. The 9:00 pm hour brought preliminary exit poll results. This, combined with turnout data, further boosted the index by another 16 percentage points. The 23:00 hour brought a record high for the confidence index – a level of 71% was recorded. This data brought the average daily confidence index on October 15 to 32%. It was 11 percentage points higher compared to the previous day.
Whether the positive momentum generated by the election results will have a more lasting trend in the financial markets and the economy as a whole, time will tell. Perhaps it will depend, among other things, on the pace at which the election promises are implemented. Promises made by the coalition that will take over our country.
The analysis was carried out thanks to the materials provided, in cooperation with the IBIMS Institute for Internet and Social Media Research.
by Agnieszka Czoska | Nov 8, 2019 | Conferences, Sentimenti research
Sentimenti = Emotions. We’ve previously discussed how to accurately analyze emotions with automated tools. Today, we’ll explain how we gathered the data that led to the creation of Sentimenti tools. This article is a guide to conducting effective research on the emotional meaning of texts.
The text was prepared for the GHOST Day machine learning conference and you can view the presentation in Polish.
Sentimenti. What emotions?
To train machine learning algorithms to automatically identify emotions in text, we first had to ask people how they feel. This seemingly simple question had to be broken down into several components.
First, what types of emotions should we consider? How many are there, and how do they differ? To answer these questions, we consulted the emotion specialists from the LOBI team. In psychology, there are various models of emotions, from simple to complex and multidimensional. We ultimately chose two models, which we now refer to as the sentiment and emotion models.
The sentiment model, based on Russell and Mehrabian’s 1977 paper, describes emotions along two axes: positive-negative and high-low arousal. As for the emotion model, we adopted the Plutchik model, both for its scientific robustness and because a portion of the Polish Slavic network had already been classified using it. This alignment allowed us to compare our findings with expert annotations, serving as a key test for accuracy.
What words?
Once we knew how to classify emotions, the next question was: what words to analyze? Our first step was focusing on the emotional meaning of words. We compared our findings with databases like WordNet and NAWL.
Our goal was to create a list of 30,000 words or meanings. Some words are ambiguous, with emotional tones shifting depending on context. For instance, “depression” can refer to both terrain and a mood disorder. We limited ourselves to a maximum of three meanings per word, each presented in context.
Thanks to the WordNet project, we learned that 27% of words have emotional meanings. These emotionally charged words took precedence in our analysis.
Sentimenti project: who participated?
To analyze emotional undertones in texts, we needed insights from a representative group of speakers. We worked with the nationwide research panel Ariadna to gather participants. Over 20,000 people took part in the study, providing data on at least 50 words each.
How We Collected Emotional Data
We designed a tool to assess word meanings on scales reflecting both sentiment and basic emotions. Participants evaluated words based on the emotional overtones they perceived in given phrases.
The study’s structure also considered participant fatigue. To ensure high-quality data, each person reviewed 150 words over three rounds, with breaks between rounds to maintain focus.
Beyond Words
Our next phase expanded beyond words to assess the emotional undertones of entire texts. Linguists have long known that the emotional meaning of a text goes beyond the sum of its words. The grammar and structure of a text also convey emotions.
For this phase, we analyzed existing reviews (e.g., hotels, doctors), as well as shorter forms like sentences and phrases. To ensure comparability with our word-level analysis, participants rated texts using the same emotional scales.
From People to AI
Sentimenti’s text classification tools now achieve high accuracy in identifying emotions, thanks to the solid dataset we built from word and text evaluations. While advanced neural networks may seem impressive, no AI can succeed without robust data to train on.
We’ve shared the details of our algorithm development both on our blog and in this scientific publication. Additionally, 20% of our word database will soon be published for researchers worldwide who study Polish emotions. This interactive database will have its own dedicated page, similar to NAWL’s list of affective words.
