Dataset Name: alexandria_earnings_transcript_sentiment_intraday
Group: sentiment
Vendor: Alexandria Technology
Data Starts at: 2000-04-27 00:00:00
Symbol Set: Global Equities
Asset Class: Equity
Data Update Time(s): 9:01 AM EST
Data Update Frequency: intraday
Alexandria provides thematic sentiment for a company's earnings calls. You can determine if the entire call is positive, neutral, or negative, as well as the Management Discussion (MD) prepared statements of Questions & Answers (QA) from analysts. In addition, you can drill down into themes. With revenues positive, costs, net income, margins and much more.
Data Contained in this Dataset
| Column | Type | Description |
|---|---|---|
| _seq | uint | Internal sequence number used to keep data rows in order |
| timestamp | string | Timestamp of the Data - America/New York Time. |
| muts | uint64 | Microseconds Unix Timestamp. An integer representation of a timestamp with microsecond precision that can be compared directly to other timestamps. |
| symbol | string | Trading Symbol or Ticker |
| ID | uint | Unique numeric Code ID assigned to every document. The combination of the Text ID and the Section |
| Call_Time | string | The date and time of the earnings call in UTC (universal time code) |
| Country | string | 3-letter country code based on ISO-3166 designation, assigned by the location of the exchange on which the stock is listed, point-in-time sensitive |
| ISIN | string | International Securities Identification Number. An international code which identifies a securities issue |
| Section | string | Identification of which part of the call transcript each row of data is derived from. The letter prefix indicates area of discussion and the number indicates the sequence order within the MD segment or Q&A segment. Numbering starts at 0 (for example, Q0 i |
| Sentiment | int | A trinary score for sentiment of the topic identified for this transcript section, derived from the the highest probable state of sentiment, 1.0 = positive, 0 = neutral, and -1.0 = negative. |
| Confidence | double | A normalization of the 'Prob_' fields showing overall match to known sentiment state alone: 0.000 = zero probability, 1.000 is absolute probability. Calculation is [max Prob_]-0.333'/0.666' |
| Topic | string | Identifies the news topic found in that section. If multiple topics are found, there will be an additional row for each other topic, showing the different Topic ID Tag and Count, but the rest of the fields will be the same. If not topic is found this fiel |
| Topic_Count | uint | The number of times the identified topic is discussed in the particular section of text |
| Name | string | Identifies the name of the person speaking |
| Title | string | Identifies the title of the person speaking |
| Affiliation | string | Identifies the company affiliation of the speaker |
| Prob_POS | double | Sentiment probability: The raw probability that the topic sentiment is positive expressed as a decimal with all three probabilities summing to 1 |
| Prob_NTR | double | Sentiment probability: The raw probability that the topic sentiment is neutral expressed as a decimal with all three probabilities summing to 1 |
| Prob_NEG | double | Sentiment probability: The raw probability that the topic sentiment is negative expressed as a decimal with all three probabilities summing to 1 |
| Call_Type | string | The indicator tells you what type of call or presentation the transcript is taken from. E - Earnings Call, G - Guidance Call, SS - Business Update Call, AS - Investor Meeting, SA - Sales & Revenue Call, CP - Conference Presentation, SR - Sales & Revenue R |
| Word_Count | uint | The count of words in that Section |
| Transcript_Type | string | T indicates this is the original transcript, "C" indicates that this is a final copy |
| Version_ID | uint | A sequential count of global documents in the order they were received. The count is universal and not company specific meaning company ABC can have count 10001 while XYZ can be 10002 |